- annotate the research Must demoted to hook Should 12; narrow Must 5 note - extend Must 6 to scripts run via an interpreter -c string - add a fallback dispatch row and comma-joined --target guidance - fall back when agentsmd-author is not installed - add the apm-workflow boundary; pin upstream apm source URL Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01KkT7RSDwDbmrM9T34b6sTi
2.2 KiB
2.2 KiB
Sources
apm-cli-installed-source
- URL: https://github.com/microsoft/apm/tree/v0.28.0/src/apm_cli/
- Note: read locally from the pipx install at
~/.local/pipx/venvs/apm-cli/lib/python3.11/site-packages/apm_cli/ - Research doc: plugins/kyberforge/docs/research/docs/microsoft-apm/sources.md
- Description: Installed apm-cli 0.28.0 source — ground truth for what apm deploys from a hook, instruction or prompt file and what it silently skips or only warns on; each Must/Should traces to the research docs' Authoring checklists or audit-only lists, or to ADR-0029, with tier moves annotated inline, and the
**/*.instructions.mdlocal-discovery glob behind the template-suffix Gotcha isprimitives/discovery.pyLOCAL_PRIMITIVE_PATTERNS; the per-target event rename maps areintegration/hook_integrator.py_HOOK_EVENT_MAP; and Step 4.2's render relies onapm install <local path>deploying the working tree to every--target, verified against 0.28.0 - Contributing files: SKILL.md, references/hook.md, references/instruction.md, references/prompt.md
- Status:
extracted
apm-docs-llms-full
- URL: https://microsoft.github.io/apm/llms-full.txt
- Research doc: plugins/kyberforge/docs/research/docs/microsoft-apm/sources.md
- Description: Published apm docs bundle — the "Hooks and commands" guide's canonical hook shape,
${PLUGIN_ROOT}, reach viatargets:rather than deprecated filename routing, and "reach for a skill, instruction, or prompt first"; the "Author a prompt" guide's one-intent rule - Contributing files: SKILL.md, references/hook.md, references/instruction.md, references/prompt.md
- Status:
extracted
adr-0029-prompt-house-rule
- URL: docs/adr/0029-prompts-are-thin-user-triggered-steering-messages.md
- Research doc: none
- Basis: docs/adr/0029-prompts-are-thin-user-triggered-steering-messages.md
- Description: The repo's prompt house rule — a prompt is a single-intent, user-triggered steering message with no procedure — and its description contract: one user-facing sentence naming the steered skills, no trigger or boundary clause
- Contributing files: references/prompt.md
- Status:
extracted