Defame1297
ef27c9751a
Why: scripts/skill-size-check.sh embedded a byte-identical 1,061-line copy
of the ADR-0020 boundary resolver only because it was also exported
through .pre-commit-hooks.yaml, whose consumers could not reach a file
inside the plugin. 4de5b6b retired that export, so the hook now runs only
in this repo and can source factory-audit's lib-boundary-resolver.sh like
validate.sh does. One copy removes the edit-one-paste-the-other hazard.
Implementation Notes:
- The hook's Python program is assembled from its own preamble, the
library's resolver and its own checks, read from quoted here-docs. The
assembled program matches the old one line for line except one comment,
and the hook's stdout, stderr and exit code are identical over every
corpus SKILL.md and the 26 differential-suite fixtures.
- The hook fails closed, naming the library, when it is missing or
defines no resolver.
- test-adr0020-contract.sh assertion 1 now pins the single copy: one
marker pair in the library, none in the hook, fail-closed on a missing
or gutted library, and a sentinel planted in a copied library that must
appear in the hook's output. 1a expects exactly one authority. 27 -> 29
passes.
- ADR-0020 and ADR-0025 carry dated amendments; gates.md and the
library, hook and mode-library comments no longer describe two copies.
- factory-audit is new on this branch, so the version-bump gate exempts
it; kyberforge is already at 2.0.0 against main's 1.6.2.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
686 lines
34 KiB
Bash
Executable File
686 lines
34 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# lib-checks-agent.sh — SOURCED, never executed.
|
|
#
|
|
# agent-audit's structural check suite: everything in its validate.sh that is
|
|
# NOT the ADR-0020 shared boundary resolver, lifted verbatim and split at the
|
|
# resolver's markers. validate.sh reassembles
|
|
#
|
|
# $KYBERFORGE_AGENT_PREAMBLE_PY
|
|
# $KYBERFORGE_RESOLVER_PY (from lib-boundary-resolver.sh)
|
|
# $KYBERFORGE_AGENT_BODY_PY
|
|
#
|
|
# in that order — the order the resolver block sat in the original file — and
|
|
# feeds the result to python3 with the agent file as argv[1] and this scripts/
|
|
# directory as argv[2]. argv[2] is what the preamble resolves the frontmatter
|
|
# allowlist against, and the body's detect_scope() walk-up and provider
|
|
# detection are unchanged from agent-audit's copy.
|
|
#
|
|
# The dimension vocabulary and the tiers here are agent-audit's and are
|
|
# deliberately NOT reconciled with lib-checks-skill.sh's. Agents take the
|
|
# ADR-0020 description gates and no body word gate at all; adding one would
|
|
# contradict the ADR.
|
|
#
|
|
# Consumed by: validate.sh, agent mode.
|
|
# shellcheck shell=bash
|
|
# shellcheck disable=SC2034
|
|
|
|
kyberforge_agent_preflight() {
|
|
# PyYAML is a HARD dependency, not a nice-to-have. The description VALUE has to
|
|
# be measured after YAML folding is resolved, and the hand-rolled reader that
|
|
# used to stand in for PyYAML disagreed with it across the 400-character FAIL
|
|
# boundary — same description, two verdicts, depending on which reader ran.
|
|
# Refusing to start is the only honest option; the repo's jq / apm / vale
|
|
# dependencies are declared the same way.
|
|
# Check the interpreter separately from the library: `python3 -c` fails the same
|
|
# way whether python3 is missing or PyYAML is, and reporting the wrong missing
|
|
# dependency sends the reader to install the wrong thing.
|
|
if ! command -v python3 > /dev/null 2>&1; then
|
|
echo "Error: python3 is required but was not found on PATH." >&2
|
|
echo " Why: skipping the ADR-0020 description and boundary-target gates would be a vacuous pass." >&2
|
|
echo " Fix: install python3 (pre-commit itself is a Python application, so it is almost certainly already present)." >&2
|
|
# Exit 2, the never-ran tier: no check ran, so this is not a findings result.
|
|
# lib-provenance-*.sh has always exited 2 here; this matches it.
|
|
exit 2
|
|
fi
|
|
|
|
if ! python3 -c 'import yaml' > /dev/null 2>&1; then
|
|
echo "Error: PyYAML is required but is not importable by python3." >&2
|
|
echo " Why: skipping the ADR-0020 description and boundary-target gates would be a vacuous pass." >&2
|
|
echo " Fix: python3 -m pip install PyYAML (or your distro's python3-yaml package)." >&2
|
|
# Exit 2, the never-ran tier: a missing hard dependency is not a findings result.
|
|
exit 2
|
|
fi
|
|
}
|
|
|
|
IFS='' read -r -d '' KYBERFORGE_AGENT_PREAMBLE_PY <<'KYBERFORGE_AGENT_PREAMBLE' || true
|
|
import sys
|
|
import os
|
|
import re
|
|
import glob
|
|
|
|
import yaml
|
|
|
|
# Output is UTF-8 for the same reason input is: under LC_ALL=C the streams
|
|
# default to ASCII, and this script's own message text carries em dashes (the
|
|
# ADR-0020 boundary SUGGESTION is one). Pinning only the reads moved the crash
|
|
# from the read to the write — a UnicodeEncodeError raised while PRINTING, after
|
|
# every check has already run, which loses the whole report and (here) flips a
|
|
# clean exit 0 into a traceback and an exit 1. read_text() in the shared
|
|
# resolver block below pins the reads; this pins the writes.
|
|
#
|
|
# Deliberately OUTSIDE the ADR-0020 shared boundary resolver block: the two
|
|
# validate.sh modes print findings, skill-size-check.sh has its own top-level
|
|
# equivalent, and the block is one sourced copy all three share, so each
|
|
# consumer's own startup stays in its own preamble.
|
|
for _stream in (sys.stdout, sys.stderr):
|
|
try:
|
|
_stream.reconfigure(encoding='utf-8')
|
|
except AttributeError: # pragma: no cover — Python < 3.7
|
|
pass
|
|
|
|
agent_file = os.path.abspath(sys.argv[1])
|
|
script_dir = sys.argv[2]
|
|
|
|
fname = os.path.basename(agent_file)
|
|
|
|
# --- Detect provider (check .agent.md before .md) ---
|
|
if fname.endswith('.agent.md'):
|
|
provider = 'copilot'
|
|
name_stem = fname[:-len('.agent.md')]
|
|
elif fname.endswith('.md'):
|
|
provider = 'claude-code'
|
|
name_stem = fname[:-len('.md')]
|
|
else:
|
|
print(f"Error: unrecognized extension '{fname}' — expected .md or .agent.md", file=sys.stderr)
|
|
sys.exit(2)
|
|
|
|
# --- Load agent-field-inventory.md ---
|
|
# The merged skill holds one references/ directory for both modes, so every
|
|
# flow-specific file is name-prefixed and the agent half of the inventory is
|
|
# agent-field-inventory.md (ADR-0025). There is no fallback to the pre-merge
|
|
# `field-inventory.md` spelling: agent-audit no longer exists, so a file at that
|
|
# name would be a stray, and silently reading it would mean auditing against an
|
|
# inventory this skill does not ship.
|
|
inv_path = os.path.normpath(os.path.join(script_dir, '..', 'references', 'agent-field-inventory.md'))
|
|
if not os.path.isfile(inv_path):
|
|
print(f"Error: agent-field-inventory.md not found at {inv_path}", file=sys.stderr)
|
|
sys.exit(2)
|
|
|
|
# Encoding is pinned to UTF-8 rather than inherited from the locale: under
|
|
# LC_ALL=C the inherited default is ASCII, and this file legitimately carries
|
|
# non-ASCII prose. read_text() in the shared resolver block below does the same
|
|
# thing for every other file; this one is read before that block is defined.
|
|
try:
|
|
with open(inv_path, encoding='utf-8') as f:
|
|
inv_content = f.read()
|
|
except UnicodeDecodeError as exc:
|
|
print(f"Error: agent-field-inventory.md at {inv_path} is not valid UTF-8 "
|
|
f"({exc.reason} at byte {exc.start}) — re-save it as UTF-8.",
|
|
file=sys.stderr)
|
|
sys.exit(2)
|
|
|
|
def parse_section_tokens(content, section_name):
|
|
lines = content.splitlines()
|
|
for i, line in enumerate(lines):
|
|
if line.strip() == f'## {section_name}':
|
|
for j in range(i + 1, len(lines)):
|
|
stripped = lines[j].strip()
|
|
if stripped and not stripped.startswith('#') and not stripped.startswith('---'):
|
|
return set(stripped.split())
|
|
return set()
|
|
|
|
cc_only_fields = parse_section_tokens(inv_content, 'claude-code-only-fields')
|
|
copilot_only_fields = parse_section_tokens(inv_content, 'copilot-only-fields')
|
|
apm_agent_allowlist = parse_section_tokens(inv_content, 'apm-agent-allowlist')
|
|
|
|
# Tools the runtime withholds from subagents regardless of the tools field
|
|
SUBAGENT_UNAVAILABLE_TOOLS = {
|
|
'AskUserQuestion', 'EnterPlanMode', 'ExitPlanMode', 'ScheduleWakeup', 'WaitForMcpServers',
|
|
}
|
|
|
|
# Copilot body length limit (chars) — content beyond this is silently truncated
|
|
COPILOT_BODY_LIMIT = 30000
|
|
|
|
# ADR-0020 description budget. An agent's name + description is preloaded into
|
|
# every session exactly like a skill's, so agents take the SAME description
|
|
# gates. These two constants are DUPLICATED in three places:
|
|
# scripts/skill-size-check.sh, lib-checks-skill.sh beside this file, and here.
|
|
# The repo-root hook's copy cannot be sourced FROM this skill — a cache-installed
|
|
# plugin's scripts cannot read files outside their own plugin directory. (The
|
|
# hook could now read these from the plugin, as it already sources
|
|
# lib-boundary-resolver.sh, but they sit in its Python preamble; hoisting them
|
|
# is a separate change.) The two copies INSIDE this skill could be
|
|
# shared (ADR-0025: two files in one skill may source a third), and are not only
|
|
# because each mode library is a verbatim lift of the pre-merge suite whose
|
|
# constants sit in its Python preamble; hoisting them is a separate change.
|
|
# tests/test-skill-size-check.sh asserts all three agree, so drift fails CI
|
|
# rather than silently diverging.
|
|
#
|
|
# Agents deliberately take NO body word gate, and adding one here would
|
|
# contradict ADR-0020: a skill body is loaded into the caller's context and
|
|
# competes with the live conversation, while an agent body becomes the system
|
|
# prompt of a fresh context. The rationale for the 900-word skill ceiling does
|
|
# not transfer. Agent body length falls out of the delegation rule instead.
|
|
DESC_SUGGEST_CHARS = 250
|
|
DESC_MAX_CHARS = 400
|
|
|
|
# --- Helpers (shared by every scope) ---
|
|
failed = False
|
|
suggestions = []
|
|
|
|
def fail(msg):
|
|
# stderr, matching scripts/skill-size-check.sh's ERROR routing. All three
|
|
# scripts in the ADR-0020 family now agree: findings that fail the run go to
|
|
# stderr, everything advisory (SUGGESTION / INFO) goes to stdout. Both repo
|
|
# callers (check-apm-agents-valid.sh, check-scope-walkup-sync.sh) capture
|
|
# `2>&1`, so nothing a human reads moves.
|
|
global failed
|
|
failed = True
|
|
print(f"FAIL {msg}", file=sys.stderr)
|
|
|
|
def suggest(msg):
|
|
suggestions.append(msg)
|
|
|
|
def info(msg):
|
|
# A check that DECLINED to run says so out loud, rather than passing
|
|
# silently. Silence is what let a whole gate family go missing unnoticed.
|
|
print(f"INFO {msg}")
|
|
|
|
PLACEHOLDER_RE = re.compile(r'(?<!`)FILL IN:[^`\n]')
|
|
|
|
|
|
KYBERFORGE_AGENT_PREAMBLE
|
|
KYBERFORGE_AGENT_PREAMBLE_PY="${KYBERFORGE_AGENT_PREAMBLE_PY%$'\n'}"
|
|
|
|
IFS='' read -r -d '' KYBERFORGE_AGENT_BODY_PY <<'KYBERFORGE_AGENT_BODY' || true
|
|
|
|
|
|
def parse_frontmatter(content):
|
|
m = FRONTMATTER_RE.match(strip_bom(content))
|
|
if not m:
|
|
return None, content
|
|
return m.group(1), strip_bom(content)[m.end():]
|
|
|
|
def extract_field(fm, field):
|
|
"""The raw text after `field:` ON ITS OWN LINE, or None.
|
|
|
|
The character class is `[^\\S\\r\\n]`, never `\\s`: under re.MULTILINE a
|
|
`\\s*` after the colon crosses the newline, so `description:` with no value
|
|
followed by `model: sonnet` captured `model: sonnet` as the description.
|
|
That made the value look present, skipped the "missing or empty" failure,
|
|
and then every ADR-0020 gate early-returned on the genuinely empty folded
|
|
value — a valueless description exited 0 with zero output on a BLOCKING
|
|
pre-push gate. This function is now used only for fields with no folding
|
|
semantics (name, tools); description goes through description_value(), the
|
|
shared resolver's YAML reader, which is the only thing that can see through
|
|
`>`, `null`, `''` and a quoted `"description"` key alike.
|
|
"""
|
|
m = re.search(rf'^{re.escape(field)}:[^\S\r\n]*(.+)', fm, re.MULTILINE)
|
|
return m.group(1).strip() if m else None
|
|
|
|
def get_frontmatter_keys(fm):
|
|
keys = set()
|
|
for line in fm.splitlines():
|
|
m = re.match(r'^([a-zA-Z][a-zA-Z0-9_-]*):', line)
|
|
if m:
|
|
keys.add(m.group(1))
|
|
return keys
|
|
|
|
def agent_description(fm, local_fname):
|
|
"""The folded description VALUE, or None if it could not be read."""
|
|
try:
|
|
return description_value(fm)
|
|
except FrontmatterError as exc:
|
|
# `exc` carries the whole clause — invalid YAML, a non-mapping block, or
|
|
# a description of the wrong type. Do not prefix a diagnosis here; the
|
|
# last one named a syntax error for two failures that have none.
|
|
fail(f"{exc} — the ADR-0020 description and boundary-target gates could "
|
|
f"not run — {local_fname}")
|
|
return None
|
|
|
|
def check_description_budget(value, local_fname, by_hand=False):
|
|
"""ADR-0020 description gates — identical for every scope.
|
|
|
|
`by_hand` is ADR-0020's hand-invocation carve-out (issue #108): an agent
|
|
carrying `disable-model-invocation: true` is absent from the model-visible
|
|
listing, so the 250-character SUGGESTION — a routing-quality budget — has
|
|
no listing to apply to. The 400-character ceiling is unaffected.
|
|
"""
|
|
if not value:
|
|
return
|
|
dlen = len(value)
|
|
if dlen > DESC_MAX_CHARS:
|
|
fail(f"description is {dlen} chars — exceeds the {DESC_MAX_CHARS}-character "
|
|
f"ADR-0020 ceiling. It is preloaded into every session whether or not the "
|
|
f"agent is invoked. Keep a trigger clause, at most one capability clause, "
|
|
f"and a boundary clause; move capability enumeration, output-format detail, "
|
|
f"composition notes and implementation detail to the body — {local_fname}")
|
|
elif dlen > DESC_SUGGEST_CHARS and not by_hand:
|
|
suggest(f"description is {dlen} chars — over the {DESC_SUGGEST_CHARS}-character "
|
|
f"ADR-0020 target (hard fail at {DESC_MAX_CHARS}). The SUGGESTION tier is "
|
|
f"what moves the corpus average; the FAIL tier only stops outliers "
|
|
f"— {local_fname}")
|
|
|
|
def check_boundary(value, fpath, local_fname, by_hand=False):
|
|
"""ADR-0020 boundary clause + resolvable boundary targets.
|
|
|
|
agent-author's SKILL.md states that an agent's boundary targets must
|
|
resolve, but until this ran no script checked it — the contract was
|
|
documented and unenforced. The resolution universe is derived from the
|
|
AGENT FILE's own location (the authoring root above it, its own apm
|
|
package, and that package's declared apm dependencies), never from this
|
|
script's path, and — when an authoring root exists — never from a deployed
|
|
.claude/ tree, so a fresh clone and a machine that has run `apm install`
|
|
return the same verdict.
|
|
"""
|
|
if not value:
|
|
return
|
|
# SUGGESTION, not FAIL: detecting the absence is deterministic, but whether
|
|
# this particular agent warrants a boundary clause is judgment. All four
|
|
# agents in this corpus currently lack one.
|
|
#
|
|
# THREE outcomes, not two: "no boundary clause" and "boundary clause I could
|
|
# not parse" are different findings (issue #110). And a hand-invoked agent is
|
|
# exempt from the clause altogether (issue #108) — the boundary-target
|
|
# resolution below still runs, because a target it DOES name should still
|
|
# resolve.
|
|
status = boundary_clause_status(value) if not by_hand else 'present'
|
|
if status == 'absent':
|
|
suggest(f"description has no boundary clause — add the prose form (\"Do not use "
|
|
f"for X — use `y` instead\") or ADR-0020's compressed form (\"Not X -> y\") "
|
|
f"so the router knows where NOT to send this agent — {local_fname}")
|
|
elif status == 'unparsed':
|
|
suggest(f"description has an arrow boundary clause (\"Not X -> y\") from which no "
|
|
f"target could be read, so the dangling-target check did not run on it — "
|
|
f"the clause is PRESENT and unparsed, not missing. Most often the target "
|
|
f"is a single word, which is deliberately not matchable bare: write it as "
|
|
f"`name` or /name — {local_fname}")
|
|
if not by_hand:
|
|
# One arrow, one target: a second name after the same arrow is resolved
|
|
# by nothing and reported by nothing (issue #107).
|
|
for first, second in multi_target_arrow_clauses(value):
|
|
suggest(f"an arrow boundary clause names more than one target ('{first}', then "
|
|
f"'{second}') and only the first is resolved — the second is checked by "
|
|
f"nothing. Split it into one arrow per target: \"Not X -> {first}. "
|
|
f"Not Y -> {second}.\" — {local_fname}")
|
|
targets = boundary_targets(value)
|
|
if not targets:
|
|
return
|
|
known = known_targets(os.path.dirname(os.path.abspath(fpath)))
|
|
if not known:
|
|
info(f"boundary-target resolution DID NOT RUN — no skill universe could be "
|
|
f"determined for this path (no authoring root above it, no apm package "
|
|
f"root, no declared apm dependencies, no deployed .claude/ or .agents/ "
|
|
f"tree). Unchecked target(s): {', '.join(targets)} — {local_fname}")
|
|
return
|
|
# blocking vs reported: a target only earns a FAIL when it is written in
|
|
# route notation or its own sentence corroborates it by naming another target
|
|
# that resolves. See the shared resolver's CORROBORATION note.
|
|
blocking, reported = unresolved_targets(value, known)
|
|
for target in blocking:
|
|
fail(f"description routes to '{target}', which resolves to no skill or agent "
|
|
f"in this monorepo, in this package, or in a package it declares in "
|
|
f"apm.yml dependencies.apm — a boundary clause naming a non-existent "
|
|
f"target sends the router nowhere — {local_fname}")
|
|
for target in reported:
|
|
suggest(f"description routes to '{target}', which resolves to no skill or agent "
|
|
f"in this monorepo, in this package, or in a package it declares in "
|
|
f"apm.yml dependencies.apm — SUGGESTION rather than FAIL because nothing "
|
|
f"else in that sentence resolves, so it is equally likely to be a tool, a "
|
|
f"file format or an English compound. If it IS a route, write it as "
|
|
f"`/{target}` or `-> {target}` and it will be checked properly — "
|
|
f"{local_fname}")
|
|
|
|
def extract_tools_list(fm):
|
|
"""Tool names from the `tools` field — inline scalar OR YAML block sequence.
|
|
|
|
Read off the PARSED mapping, never off extract_field(). That function's
|
|
capture is newline-bounded on purpose (`[^\\S\\r\\n]*(.+)`), so a `tools:`
|
|
written as a block sequence — the shape Copilot agent files use — captured
|
|
nothing at all and the subagent-unavailable-tool check silently stopped
|
|
firing on exactly the files it was written for. Both spellings are legal
|
|
YAML, so both are read here.
|
|
"""
|
|
try:
|
|
data = yaml.safe_load(fm)
|
|
except Exception:
|
|
# Not this function's failure to report: the frontmatter's validity is
|
|
# decided (and failed) by agent_description() on the same text.
|
|
return set()
|
|
if not isinstance(data, dict):
|
|
return set()
|
|
val = data.get('tools')
|
|
if isinstance(val, list):
|
|
items = [str(item).strip() for item in val]
|
|
elif isinstance(val, str):
|
|
items = re.split(r'[\s,]+', val.strip())
|
|
else:
|
|
return set()
|
|
return {item for item in items if item}
|
|
|
|
def is_copilot_cloud_ide(fpath):
|
|
"""True if the file is a cloud/IDE Copilot agent (name is optional for these)."""
|
|
return '.github/copilot/agents' in os.path.abspath(fpath).replace(os.sep, '/')
|
|
|
|
# --- Detect scope ---
|
|
# APM_TYPE_RE matches a top-level (column-0) `type:` line in apm.yml whose value is
|
|
# exactly one of the four package content types. Group 1 captures an optional
|
|
# opening quote; \1 requires the same character (or nothing) to close it, so
|
|
# "skill" and '"skill"' both match but a mismatched quote doesn't. The value
|
|
# must then be followed by whitespace or end-of-line — not just a non-word
|
|
# character — so a malformed value like `prompts-only` is correctly rejected
|
|
# instead of false-matching on the `prompts` prefix.
|
|
APM_TYPE_RE = re.compile(r"^type:\s*(['\"]?)(instructions|skill|hybrid|prompts)\1(?:\s|$)")
|
|
|
|
def find_apm_package_root(apm_yml_path):
|
|
"""Return True if apm_yml_path has a top-level type: line (i.e. is a package
|
|
manifest, not a type:-less marketplace-only apm.yml)."""
|
|
# errors='replace', not a hard failure: this only asks whether a `type:`
|
|
# line exists, and a stray undecodable byte elsewhere in someone else's
|
|
# apm.yml must not abort scope detection.
|
|
with open(apm_yml_path, encoding='utf-8', errors='replace') as f:
|
|
for line in f:
|
|
if APM_TYPE_RE.match(line):
|
|
return True
|
|
return False
|
|
|
|
def detect_scope(start_dir):
|
|
home = os.path.expanduser('~')
|
|
original_start = os.path.abspath(start_dir)
|
|
# Agent files conventionally live exactly two path segments below their
|
|
# scope root — <root>/.claude/agents, <root>/.github/agents,
|
|
# <root>/.copilot/agents, or <root>/.apm/agents (see new-agent.sh's
|
|
# CC_DIR/CP_DIR and user-scope dirs). Stripping those two segments
|
|
# recovers the same root new-agent.sh would have been invoked with to
|
|
# produce this exact file, independent of how far the walk below has to
|
|
# travel to find (or fail to find) a marker — mirrors new-agent.sh's
|
|
# `root` vs `current` distinction even though validate.sh is handed a
|
|
# file's directory, not the scope root itself.
|
|
#
|
|
# That arithmetic is only trustworthy when the path actually has this
|
|
# shape: parent directory literally named "agents", grandparent one of
|
|
# the four known scope-dir names. A hand-placed or otherwise
|
|
# non-conventional agent file (never produced by new-agent.sh) has no
|
|
# such guarantee — blindly trusting two-segments-up there could point at
|
|
# an unrelated ancestor. conventional_shape gates every use of
|
|
# conventional_root below; when it's false, the walked-to `current`
|
|
# directory is used instead, the same fallback this function used before
|
|
# conventional_root existed.
|
|
scope_dir_name = os.path.basename(os.path.dirname(original_start))
|
|
conventional_shape = (
|
|
os.path.basename(original_start) == 'agents'
|
|
and scope_dir_name in ('.claude', '.github', '.copilot', '.apm')
|
|
)
|
|
conventional_root = os.path.dirname(os.path.dirname(original_start))
|
|
current = original_start
|
|
while True:
|
|
# The filesystem root is never a candidate, the same guard the shared
|
|
# resolver's walk-up loops carry. Without it a file under a marker-less
|
|
# temp directory walked all the way to `/` and returned it as the scope
|
|
# root, which then reported `counterpart file not found:
|
|
# /.claude/agents/<name>.md` — a path that names someone else's machine,
|
|
# not the user's project. When the walk runs out, the agent file's own
|
|
# directory (or its conventional root) is the honest answer.
|
|
if _is_fs_root(current):
|
|
return 'project', conventional_root if conventional_shape else original_start
|
|
apm_yml = os.path.join(current, 'apm.yml')
|
|
if os.path.isfile(apm_yml) and find_apm_package_root(apm_yml):
|
|
return 'plugin', current
|
|
# $HOME is the user-scope boundary — checked before the .git test
|
|
# below, so a dotfiles-managed $HOME (yadm, chezmoi bare-repo, etc.)
|
|
# can't shadow user scope by being its own .git repo. 'user' scope
|
|
# requires EITHER start_dir to BE $HOME itself (no walk-up — the
|
|
# new-agent.sh "root exactly $HOME" case) OR start_dir to sit at the
|
|
# conventional two-segments-below-root depth (i.e. $HOME IS that
|
|
# root, matching the real ~/.claude/agents or ~/.copilot/agents
|
|
# shape). Any other walk-up into $HOME — a marker-less directory
|
|
# nested deeper than that convention — resolves to project scope
|
|
# instead: a stray directory under $HOME can't be silently
|
|
# redirected into the shared global ~/.claude or ~/.copilot agent
|
|
# directories.
|
|
if current == home:
|
|
if original_start == home or (conventional_shape and conventional_root == home):
|
|
return 'user', home
|
|
return 'project', conventional_root if conventional_shape else current
|
|
# .git is a directory in a normal checkout but a file (`gitdir: ...`)
|
|
# in a git worktree — exists() covers both. Returns conventional_root,
|
|
# not current: new-agent.sh's project-scope file placement always
|
|
# uses its `$ROOT` argument directly, never the walked-up `.git`
|
|
# location, so a <root> one or more levels below the repo's .git
|
|
# (a subdirectory of a larger git-tracked tree — explicitly a
|
|
# supported case per new-agent.sh's usage text) must resolve to the
|
|
# same root new-agent.sh actually wrote to, not to the .git dir —
|
|
# unless the path lacks the conventional shape, in which case that
|
|
# arithmetic isn't trustworthy and current is used instead.
|
|
if os.path.exists(os.path.join(current, '.git')):
|
|
return 'project', conventional_root if conventional_shape else current
|
|
parent = os.path.dirname(current)
|
|
if parent == current:
|
|
return 'project', conventional_root if conventional_shape else current
|
|
current = parent
|
|
|
|
agent_dir = os.path.dirname(agent_file)
|
|
scope, scope_root = detect_scope(agent_dir)
|
|
|
|
# --- Plugin/APM scope: single vendor-neutral file, no counterpart ---
|
|
def check_apm_agent_file(fpath, allowlist, stem):
|
|
local_fname = os.path.basename(fpath)
|
|
try:
|
|
content = read_text(fpath)
|
|
except EncodingError as exc:
|
|
fail(f"file is {exc}. Nothing could be measured, so this is a hard "
|
|
f"failure, not a skip — {local_fname}")
|
|
return
|
|
except OSError as exc:
|
|
# A path that cannot be opened gets a FAIL line naming it, not a bare
|
|
# FileNotFoundError traceback. scripts/check-apm-agents-valid.sh takes
|
|
# this path for an agent file deleted from the worktree but still
|
|
# tracked in the index — a real, expected state, and the caller needs to
|
|
# be told which file, not handed an interpreter stack.
|
|
fail(f"could not be read ({exc.strerror or exc}): {fpath}. Nothing could "
|
|
f"be measured, so this is a hard failure, not a skip — {local_fname}")
|
|
return
|
|
|
|
fm, body = parse_frontmatter(content)
|
|
if fm is None:
|
|
fail(f"no parseable YAML frontmatter block — expected a `---` line, the fields, "
|
|
f"then a closing `---` line (a BOM, leading blank lines, trailing spaces "
|
|
f"after either marker and CRLF endings are all tolerated). Nothing could be "
|
|
f"measured, so this is a hard failure, not a skip — {local_fname}")
|
|
return
|
|
|
|
# The apm-agent.md template embeds its authoring guidance as HTML
|
|
# comments inside the frontmatter block (so they render invisible in a
|
|
# Markdown preview but stay visible in the raw file). get_frontmatter_keys
|
|
# silently ignores any line that isn't a `key:` match, so a comment left
|
|
# behind at ship time would otherwise pass unnoticed — yet apm compile
|
|
# copies this frontmatter verbatim to both harnesses, and `<!-- -->` is
|
|
# not valid YAML, so yaml.safe_load breaks on both downstream (ADR-0016).
|
|
if re.search(r'<!--|-->', fm):
|
|
fail(f"frontmatter still contains template HTML comments (<!-- ... -->) "
|
|
f"— delete them before shipping — {local_fname}")
|
|
|
|
# Allowlist: the permitted keys are data, read at load time from
|
|
# references/agent-field-inventory.md's `## apm-agent-allowlist` section — do not
|
|
# restate them here, or this comment goes stale the next time that line
|
|
# changes. apm compile verbatim-copies frontmatter to every target, so a key
|
|
# outside the list is unsafe on at least one harness (ADR-0016). Note the
|
|
# list admits denylist-shaped restrictions (disallowedTools) but never
|
|
# allowlist-shaped ones (tools), whose value shape differs per harness.
|
|
fm_keys = get_frontmatter_keys(fm)
|
|
for key in sorted(fm_keys):
|
|
if key not in allowlist:
|
|
fail(f"field '{key}' is not in the vendor-neutral APM agent allowlist "
|
|
f"({', '.join(sorted(allowlist))}) — {local_fname}")
|
|
|
|
# name — required, kebab-case, must match filename stem (file is <name>.agent.md)
|
|
name_val = extract_field(fm, 'name')
|
|
if not name_val:
|
|
fail(f"name field is missing or empty — {local_fname}")
|
|
else:
|
|
if not re.match(r'^[a-z0-9]+(-[a-z0-9]+)*$', name_val):
|
|
fail(f"name '{name_val}' is not kebab-case — {local_fname}")
|
|
if name_val != stem:
|
|
fail(f"name '{name_val}' does not match filename stem '{stem}' — {local_fname}")
|
|
|
|
# description — required, non-empty, no placeholder
|
|
# Presence is decided on the FOLDED value, never on a line regex. Deciding
|
|
# it on extract_field's raw capture is what let `description:` with no value
|
|
# pass this gate in total silence: the capture picked up the next key, so
|
|
# "missing or empty" never fired, and every ADR-0020 check below then
|
|
# early-returned on the empty folded value. Exit 0, zero output, no gate run.
|
|
folded = agent_description(fm, local_fname)
|
|
if folded is None:
|
|
pass # frontmatter is not valid YAML — agent_description already failed
|
|
elif not folded:
|
|
fail(f"description field is missing or empty — {local_fname}")
|
|
else:
|
|
if PLACEHOLDER_RE.search(folded):
|
|
fail(f"description contains unfilled FILL IN: placeholder — {local_fname}")
|
|
by_hand = hand_invoked(fm)
|
|
check_description_budget(folded, local_fname, by_hand)
|
|
check_boundary(folded, fpath, local_fname, by_hand)
|
|
|
|
# body — required, non-empty, no placeholder; same Copilot truncation risk
|
|
# applies since this file compiles verbatim into a real Copilot file downstream.
|
|
if not body.strip():
|
|
fail(f"system prompt body is empty — {local_fname}")
|
|
else:
|
|
if PLACEHOLDER_RE.search(body):
|
|
fail(f"body contains unfilled FILL IN: placeholder — {local_fname}")
|
|
if len(body) > COPILOT_BODY_LIMIT:
|
|
suggest(f"body exceeds {COPILOT_BODY_LIMIT:,} characters ({len(body):,} chars) — "
|
|
f"content beyond the limit is silently truncated by the Copilot runtime "
|
|
f"once apm compile emits it downstream — {local_fname}")
|
|
|
|
if scope == 'plugin':
|
|
check_apm_agent_file(agent_file, apm_agent_allowlist, name_stem)
|
|
for s in suggestions:
|
|
print(f"SUGGESTION {s}")
|
|
sys.exit(1 if failed else 0)
|
|
|
|
# --- Project/user scope: unchanged CC/Copilot pair validation ---
|
|
|
|
# --- Derive counterpart path ---
|
|
if scope == 'project':
|
|
if provider == 'claude-code':
|
|
counterpart = os.path.join(scope_root, '.github', 'agents', name_stem + '.agent.md')
|
|
counterpart_provider = 'copilot'
|
|
else:
|
|
counterpart = os.path.join(scope_root, '.claude', 'agents', name_stem + '.md')
|
|
counterpart_provider = 'claude-code'
|
|
else: # user
|
|
home = os.path.expanduser('~')
|
|
if provider == 'claude-code':
|
|
counterpart = os.path.join(home, '.copilot', 'agents', name_stem + '.agent.md')
|
|
counterpart_provider = 'copilot'
|
|
else:
|
|
counterpart = os.path.join(home, '.claude', 'agents', name_stem + '.md')
|
|
counterpart_provider = 'claude-code'
|
|
|
|
def check_file(fpath, file_provider):
|
|
local_fname = os.path.basename(fpath)
|
|
try:
|
|
content = read_text(fpath)
|
|
except EncodingError as exc:
|
|
fail(f"file is {exc}. Nothing could be measured, so this is a hard "
|
|
f"failure, not a skip — {local_fname}")
|
|
return
|
|
except OSError as exc:
|
|
# Same reason as check_apm_agent_file's: a diagnostic naming the path
|
|
# beats a FileNotFoundError traceback. The counterpart is pre-checked at
|
|
# the bottom of this script, but agent_file itself never was.
|
|
fail(f"could not be read ({exc.strerror or exc}): {fpath}. Nothing could "
|
|
f"be measured, so this is a hard failure, not a skip — {local_fname}")
|
|
return
|
|
|
|
fm, body = parse_frontmatter(content)
|
|
if fm is None:
|
|
fail(f"no parseable YAML frontmatter block — expected a `---` line, the fields, "
|
|
f"then a closing `---` line (a BOM, leading blank lines, trailing spaces "
|
|
f"after either marker and CRLF endings are all tolerated). Nothing could be "
|
|
f"measured, so this is a hard failure, not a skip — {local_fname}")
|
|
return
|
|
|
|
# name — required for CC and Copilot CLI; optional for Copilot cloud/IDE agents
|
|
cloud_ide = (file_provider == 'copilot' and is_copilot_cloud_ide(fpath))
|
|
name_val = extract_field(fm, 'name')
|
|
if not cloud_ide:
|
|
if not name_val:
|
|
fail(f"name field is missing or empty — {local_fname}")
|
|
else:
|
|
if not re.match(r'^[a-z0-9]+(-[a-z0-9]+)*$', name_val):
|
|
fail(f"name '{name_val}' is not kebab-case — {local_fname}")
|
|
# Stem check applies to Copilot CLI only; CC docs say filename need not match name
|
|
if file_provider == 'copilot':
|
|
stem = local_fname[:-len('.agent.md')]
|
|
if name_val != stem:
|
|
fail(f"name '{name_val}' does not match filename stem '{stem}' — {local_fname}")
|
|
elif name_val and not re.match(r'^[a-z0-9]+(-[a-z0-9]+)*$', name_val):
|
|
# cloud/IDE: name is optional, but if present it must be valid
|
|
fail(f"name '{name_val}' is not kebab-case — {local_fname}")
|
|
|
|
# description
|
|
# Presence is decided on the FOLDED value, never on a line regex. Deciding
|
|
# it on extract_field's raw capture is what let `description:` with no value
|
|
# pass this gate in total silence: the capture picked up the next key, so
|
|
# "missing or empty" never fired, and every ADR-0020 check below then
|
|
# early-returned on the empty folded value. Exit 0, zero output, no gate run.
|
|
folded = agent_description(fm, local_fname)
|
|
if folded is None:
|
|
pass # frontmatter is not valid YAML — agent_description already failed
|
|
elif not folded:
|
|
fail(f"description field is missing or empty — {local_fname}")
|
|
else:
|
|
if PLACEHOLDER_RE.search(folded):
|
|
fail(f"description contains unfilled FILL IN: placeholder — {local_fname}")
|
|
by_hand = hand_invoked(fm)
|
|
check_description_budget(folded, local_fname, by_hand)
|
|
check_boundary(folded, fpath, local_fname, by_hand)
|
|
|
|
# body
|
|
if not body.strip():
|
|
fail(f"system prompt body is empty — {local_fname}")
|
|
else:
|
|
if PLACEHOLDER_RE.search(body):
|
|
fail(f"body contains unfilled FILL IN: placeholder — {local_fname}")
|
|
# Copilot body length limit
|
|
if file_provider == 'copilot' and len(body) > COPILOT_BODY_LIMIT:
|
|
suggest(f"body exceeds {COPILOT_BODY_LIMIT:,} characters ({len(body):,} chars) — content beyond the limit is silently truncated by the Copilot runtime — {local_fname}")
|
|
|
|
# CC-only fields in Copilot file
|
|
if file_provider == 'copilot':
|
|
fm_keys = get_frontmatter_keys(fm)
|
|
for key in sorted(fm_keys):
|
|
if key in cc_only_fields:
|
|
fail(f"CC-only field '{key}' present in Copilot file — {local_fname}")
|
|
|
|
# Copilot-only fields in CC file
|
|
if file_provider == 'claude-code':
|
|
fm_keys = get_frontmatter_keys(fm)
|
|
for key in sorted(fm_keys):
|
|
if key in copilot_only_fields:
|
|
fail(f"Copilot-only field '{key}' present in CC file — {local_fname}")
|
|
|
|
# Subagent-unavailable tools listed in tools field
|
|
tools = extract_tools_list(fm)
|
|
unavailable = tools & SUBAGENT_UNAVAILABLE_TOOLS
|
|
for tool in sorted(unavailable):
|
|
suggest(f"'{tool}' is listed in tools but is never available to subagents — the runtime withholds it regardless — {local_fname}")
|
|
|
|
# --- Check counterpart exists ---
|
|
if not os.path.isfile(counterpart):
|
|
fail(f"counterpart file not found: {counterpart}")
|
|
sys.exit(1)
|
|
|
|
# --- Check both files ---
|
|
check_file(agent_file, provider)
|
|
check_file(counterpart, counterpart_provider)
|
|
|
|
for s in suggestions:
|
|
print(f"SUGGESTION {s}")
|
|
|
|
sys.exit(1 if failed else 0)
|
|
KYBERFORGE_AGENT_BODY
|
|
KYBERFORGE_AGENT_BODY_PY="${KYBERFORGE_AGENT_BODY_PY%$'\n'}"
|