alex
33180d6e04
AGENTS.md is now the canonical instruction file, with CLAUDE.md, .cursorrules, and .github/copilot-instructions.md as symlinks to it. This is simpler and more intuitive - the main file is at the root, not buried in .github/. Updated all references across agents, commands, skills, and .memory/.
33 lines
2.5 KiB
Markdown
33 lines
2.5 KiB
Markdown
## Agent Memory Write Access
|
|
|
|
**Decision:** Enable `permission.edit: allow` for all seven agents with memory recording duties (reviewer, tester, explorer, researcher, critic, sme, designer) so they can write `.memory/*` files directly.
|
|
|
|
**Rationale:** These agents have explicit memory duties (recording verdicts, discoveries, research findings, guidance, design decisions) but previously had `permission.edit: deny`, making those duties impossible. The lead had to relay all memory writes, losing fidelity and adding overhead.
|
|
|
|
**Implementation:**
|
|
- Changed `permission.edit: deny` → `permission.edit: allow` in all seven agent files.
|
|
- Added instruction-level guardrails in each agent to restrict edits to `.memory/*` only (code/source remains read-only).
|
|
- Path-scoped `permission.edit` is not supported by OpenCode, so instruction-level guardrails are the enforcement mechanism.
|
|
|
|
**Affected files:** `agents/reviewer.md`, `agents/tester.md`, `agents/explorer.md`, `agents/researcher.md`, `agents/critic.md`, `agents/sme.md`, `agents/designer.md`.
|
|
|
|
**Risk:** Agents could theoretically edit non-memory files since the config-level permission is `allow`. Mitigation is instruction-level enforcement, which is effective but not mechanical.
|
|
|
|
See [Plan: Agent Memory Write Access](plans/agent-memory-write-access.md) | See [Knowledge: Permission Model](knowledge.md#permission-model)
|
|
|
|
## Cross-Tool Instruction File Symlink Strategy
|
|
|
|
**Decision:** Use `AGENTS.md` as the single source-of-truth instruction file and represent `CLAUDE.md`, `.cursorrules`, and `.github/copilot-instructions.md` as symlinks to it.
|
|
|
|
**Rationale:** The previous multi-file sync model required manual propagation/merge logic and could drift. Symlinks remove synchronization overhead and guarantee tool-level consistency by construction.
|
|
|
|
**Implementation:**
|
|
- Updated `AGENTS.md` "Cross-Tool Instruction Files" guidance to document the symlink pattern and initialization/joining workflow.
|
|
- Removed session-start instruction in `AGENTS.md` that required reading additional tool-specific instruction files for merge reconciliation.
|
|
- Updated `agents/librarian.md` responsibilities from multi-file sync/merge to maintaining `AGENTS.md` plus symlink verification.
|
|
- Updated `agents/lead.md` PHASE-WRAP and Documentation Completion Gate to reference `AGENTS.md` instead of syncing four files.
|
|
|
|
**Affected files:** `AGENTS.md`, `agents/librarian.md`, `agents/lead.md`, `.memory/knowledge.md`.
|
|
|
|
See [Knowledge: Project Overview](knowledge.md#project-overview)
|