mirror of
https://github.com/kevinveenbirkenbach/computer-playbook.git
synced 2026-11-06 02:54:26 +00:00
CLAUDE.md and GEMINI.md existed as per-runtime extensions of AGENTS.md, and only one of them carried anything at all: GEMINI.md stated that it had no additions, while CLAUDE.md held rules that bind every runtime anyway — the permission announcement, the make-over-raw preference, the loop, chain and heredoc bans, the stream-the-log-to-/tmp rule, the CI-evidence rule, the push ban and the comment rule. A rule that binds every agent does not belong in one agent's file. AGENTS.md absorbs them and now states that no tool-specific extension file exists; agents whose runtime auto-loads a different filename reach it through their own configuration instead. The filenames were machinery as much as prose. The PR templates, the branch and pull-request scope tables, the settings and security docs that justified the loop deny by "the textual CLAUDE.md rule", six requirement documents whose push instruction linked ../../CLAUDE.md, and a test docstring citing the shell-loop ban all named them, and now name AGENTS.md. scripts/meta/resolve/pr/scope.sh deliberately keeps matching CLAUDE.md and GEMINI.md: this change deletes them, and without those patterns the change itself would not classify as agent-scope. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2.5 KiB
2.5 KiB
Summary
Briefly describe the change to the agent instruction files and the expected effect.
Examples:
- Add a new repository rule to
AGENTS.md - Fix contradictory guidance between
AGENTS.mdanddocs/agents/* - Improve instruction clarity for
AGENTS.md
Template Type
Select the primary intent of this PR:
- Feature - Adds or extends agent guidance or workflow support
- Fix - Repairs incorrect, unclear, or conflicting agent guidance
Affected Files
List the touched agent instruction files.
AGENTS.mdroles/<role>/AGENTS.mddocs/agents/*
Additional notes:
- Any other related instruction or documentation files:
Change Type
Select the semantic version impact of this change:
- Major - Breaking change
- Minor - New backwards-compatible feature
- Patch - Small improvement or compatible adjustment
Change Details
Explain what changed and why.
Key points:
- What instruction, workflow, or policy changed?
- Why is this guidance needed or why was the previous guidance insufficient?
- How does this interact with
AGENTS.mdas the repository-wide source of truth? - Which alternatives were considered?
Validation
Describe how the instruction change was validated.
- Conflicting or ambiguous guidance checked
- Consistency between
AGENTS.md,roles/<role>/AGENTS.md, anddocs/agents/*verified - Examples, workflows, or affected contributor paths reviewed
Security Impact
Indicate whether this change has security implications.
- No relevant security impact
- Security impact present
If security impact is present, explain:
- Affected permissions, destructive actions, secrets, or safety guardrails:
- Risk reduction, new exposure, or compatibility considerations:
- Security-specific validation performed:
Review Focus
Help reviewers focus on the riskiest parts of this PR. For repository-wide contribution and review expectations, see CONTRIBUTING.md.
- Highest-risk instructions, assumptions, or policy changes:
- Cross-file consistency or contradiction concerns:
- Specific feedback requested from reviewers:
Definition of Done (DoD)
- The implementation follows the Definition of Done, and the contribution guidelines in CONTRIBUTING.md were considered and applied during implementation.
Additional Notes
Add any reviewer context for rollout, policy interpretation, or follow-up work.