Files

Defame1297 74f5e1840d test: run Chunk 2 and governance behavioral tests; fix failing rules

13 manual scenarios run across instructions and governance layers (two
rounds for failures). Fixed four rules that lost to RLHF defaults:

- Exploratory question format: tightened with boundary framing; added
  @import CONTEXT.md to repo CLAUDE.md and a standing rule to check
  docs/adr/ and ROADMAP resolved entries before answering design questions
  (3-round iteration to resolve)
- File-edit intent: added counter-example to stop clarification-seeking
- Push confirmation: reframed as "do not call the tool" not "ask first"
- Secrets rule: extended to cover credential reproduction in response
  text and usage examples, with explicit placeholder requirement

Scenario 4 (push confirmation) inconclusive — no remote configured.
Governance scenario 3 (HITL on real infra) untestable — Nginx not installed.
Both share the same root cause: agent delegates to permission system.

Also corrects stale skill list in docs/spec/overview.md (12 actual
deployed skills vs 16 names previously listed).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-05-17 11:44:56 +00:00

2.3 KiB

Raw Blame History

Overview

Current deployed state of this repo — what you get if you run install.sh today. Updated at the close of each chunk and in the same PR as any behavior change.

Last updated: 2026-05-17

What is deployed

Skills

12 skills deployed to ~/.agents/skills/ via install.sh. Available as slash commands in Claude Code via ~/.claude/skills/ → ~/.agents/skills/ symlink. All 12 are first-draft placeholders pending rebuild in Chunk 3.

Current skills: caveman, diagnose, grill-me, grill-with-docs, improve-codebase-architecture, prototype, tdd, to-issues, to-prd, triage, write-a-skill, zoom-out.

Claude Code configuration

~/.claude/CLAUDE.md — global config index; always-on rules + content index pointers
~/.claude/core/instructions/ — coding, git, testing, governance instruction files
~/.claude/settings.json — Claude Code settings

Governance layer

core/instructions/governance.md loads into every Claude Code session via @import in ~/.claude/CLAUDE.md. Covers: hard prohibitions on secrets and data, data classification tiers, HITL requirements, sycophancy resistance, deterministic execution preference.

What works end-to-end

install.sh runs idempotently — safe to re-run after changes
Provider adapter pattern: providers/*/provider-manifest.sh auto-discovered by install.sh
Governance rules take effect at session start without any manual loading step
Skills available as slash commands immediately after install

What is not yet deployed

sync.sh — pulls updates into existing projects (Chunk 6)
init-project.sh — bootstraps a new project (Chunk 6)
Copilot provider adapter (Chunk 7)
Formal CI/pre-commit enforcement of governance rules (Chunk 6)

For chunk planning and open questions, see docs/ROADMAP.md.

Recent changes

2026-05-17 — behavioral tests fully resolved: CONTEXT.md now always-loaded via @import in repo CLAUDE.md; standing rule added to check docs/adr/ and ROADMAP resolved entries before answering design questions; communication/behavior and secrets rules tightened; Chunk 2 and Governance Phase 1 ✅ complete
2026-05-17 — added LESSONS.md (issue 0013) and docs/spec/ (issue 0014); refactored docs/VISION.md to goals/intent only

2.3 KiB Raw Blame History