compound-eng-md-docs@5.1.7
VERIFIED· install onlyPublisher claims: "Manages project documentation: CLAUDE.md, AGENTS.md, README.md, CONTRIBUTING.md, DOCS.md. Use when asked to update, create, or init these context files. Not for general markdown editing." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
What changed since 5.1.5
vet-skills diff compound-eng-md-docs 5.1.5 5.1.7In the sandbox, this version reached for nothing 5.1.5 did not. Compared from the two recorded runs, not from source.
5.1.5 was not run in the sandbox (static only); the comparison covers what static analysis recorded only.
The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-21 and scored it 93/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
Verify and fix AGENTS.md against the actual codebase. See [update-agents.md](./update-agents.md) for the full verification workflow.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.3. Write AGENTS.md; create the CLAUDE.md symlink only when needed (optional, see [init-agents.md](./init-agents.md#claude-code-compatibility))Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.…nction signatures, type definitions). Verify against actual code the same way as AGENTS.md. Never auto-create DOCS.md; only update existing. When a doc prescribes a machine-consumed shape (a JSON artifact, con…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.If AGENTS.md exists: warn user, suggest update workflow instead. Allow override with `--force`.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.- [update-agents.md](./references/update-agents.md).Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.…xt file (works with Claude Code, Codex, Kilocode). During Initialize Context or Update Context Files workflows only: if CLAUDE.md exists without AGENTS.md, confirm with the user first (Ask via AskUserQuestion (Claude Code; load with T…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.…multi-step process producing concrete artifacts). Manages project documentation: CLAUDE.md, AGENTS.md, README.md, CONTRIBUTING.md. Use when asked to update, create, or init these context files. Not for general markdown editing. ## Sco…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.…ed symlink out there as a one-line text file unless `core.symlinks` is enabled. Edit and Write also refuse to write through a symlink and redirect the edit to AGENTS.md | | Existing `CLAUDE.md` symlink to AGENTS.md | Leave it unless the us…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.- [Update context files workflow](artifact/references/update-agents.md)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.If CLAUDE.md exists but AGENTS.md doesn't: migrate (rename to AGENTS.md; add a CLAUDE.md symlink only if a harness or session needs it, per [Claude Code compatibility](#claude-code-compatibility)).Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.…sLoaded` hooks do not fire for a natively read AGENTS.md (they do fire through a CLAUDE.md symlink or `@AGENTS.md` import), and directories added with `--add-dir` while `CLAUDE_CODE_ADDITIONAL_DIRECTORIES_CLAUDE_MD` is set load their CLA…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.…ense/Terms of Use: MIT-0 ## Use Case: Developers use this skill to create or update project context and documentation files, including AGENTS.md, CLAUDE.md, README.md, CONTRIBUTING.md, and existing DOCS.md, with content checked against…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.…essions started above a package without verified later loading of its guidance, add a short conditional link in the effective root instruction file (`AGENTS.md` or `AGENTS.override.md`), such as "Before editing `packages/api/`, read `packa…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.…; AGENTS.md loads natively | | `CLAUDE.local.md` or a real `CLAUDE.md` present | AGENTS.md is not loaded. Either add a CLAUDE.md next to AGENTS.md containing `@AGENTS.md` (or put the import at the…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.