Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/auerbachb/claude-code-config/monitornpx skills add auerbachb/claude-code-config --skill monitorgit clone --depth 1 https://github.com/auerbachb/claude-code-configWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00119 | $0.04866 |
| Opus 5 | $0.00060 | $0.02433 |
| Sonnet 5 | $0.00024 | $0.00973 |
| Haiku 4.5 | $0.00012 | $0.00487 |
Grade A, and why
monitor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit the open PR backlog and confirm that all four AI code reviewers have actually engaged on each PR, then post the missing trigger comments. The four reviewers and their exact bot logins / trigger strings are:
| Reviewer | Bot login | Trigger string |
|---|---|---|
| CodeRabbit | coderabbitai[bot] |
@coderabbitai full review |
| CodeAnt | codeant-ai[bot] |
@codeant-ai review |
| BugBot (Cursor) | cursor[bot] |
@cursor review |
| Graphite | graphite-app[bot] |
@graphite-app re-review |
Graphite known outage (issue #610): Graphite has shown zero engagement — no comments, no check-runs — on every PR since 2026-05-08 (confirmed repo-wide, not per-PR or docs-only). A ❌ in the Graphite column most likely reflects this ongoing outage, not a fresh gap; see
.claude/reference/codeant-graphite-supplemental.mdfor evidence and the re-enablement path. Still triggered per Step 5 — the outage is a user-side fix (GitHub App reinstall/billing), not a reason to stop auditing.
/monitor is audit-and-trigger only. It is the action-oriented sibling of read-only /status: where /status reports merge-readiness, /monitor reports reviewer coverage and closes gaps. It does not drive the fix/resolve loop (that stays with /fixpr and the per-PR coding threads) and it never auto-flips drafts, auto-merges, or modifies review-bot config.
Scope boundaries (HARD STOPS)
- Never auto-flip a draft to ready-for-review. Surface it and ask; only the user runs
gh pr ready <N>. - Never post
@coderabbitai full reviewwhen CodeRabbit is rate-limited, or when the per-PR 2-explicit-triggers/hour cap is reached, or when the account hourly budget is exhausted (cr-review-hourly.sh). - Never auto-merge, dismiss reviews, or resolve threads — that is
/fixpr//wrapterritory. - The other three triggers (
@codeant-ai review,@cursor review,@graphite-app re-review) are not hourly-capped, but none is free of consequence — BugBot is per-seat and spend-metered (#1199) — so only post for a missing reviewer, and never re-nudge a BugBot that already refused this HEAD.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 315 lines · 119 tokens per session scan A e9dfd8a9349c
monitor is a skill published in the GitHub repository auerbachb/claude-code-config (5 stars, last pushed 2d ago), licensed MIT. It adds 119 tokens to every session and 4,866 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
fixer
Surgical code fixer for Bug Hunter. Implements minimal, precise fixes for verified bugs. Uses doc-lookup (Context Hub + Context7) to verify correct API usage in patches. Respects fix strategy classifications (safe-autofix vs manual-review vs larger-refactor).
referee
Final arbiter for Bug Hunter. Receives Hunter findings and Skeptic challenges, independently re-reads code, and delivers authoritative verdicts with CVSS scoring and proof-of-concept generation for security findings.
commit-security-scan
Scan code changes for security vulnerabilities using Bug Hunter-native artifacts and STRIDE context. Use whenever the user asks for PR security review, commit-diff scanning, staged-change security checks, branch-comparison security review, or pre-merge security analysis of changed code.
decompose
Decompose project or track into modules with dependency mapping. Project scope updates architecture.md and derives .ai-context.md. Track scope generates hld.md (always) and lld.md (when --lld or High-complexity module triggers it) — design-mandated artifacts that drive implement, deploy-checklist, and upload sign-off.
adr
Create and manage Architecture Decision Records. Documents significant technical decisions with context, alternatives, and consequences. Also supports evaluate (assess proposals) and design (system design) modes.
deploy-checklist
Pre-deployment verification checklist. Generates customized checklists based on tech-stack with rollback triggers. Auto-invoked by /draft:upload.