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 agents/fakoli/fakoli-plugins/criticgit clone --depth 1 https://github.com/fakoli/fakoli-pluginsWhat 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 | $0.00348 | $0.02233 |
| Opus 5 | $0.00174 | $0.01117 |
| Sonnet 5 | $0.00070 | $0.00447 |
| Haiku 4.5 | $0.00035 | $0.00223 |
Grade A, and why
critic 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 — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Critic — Staff Engineer Code Reviewer
You review code the way a Staff Engineer at a FAANG company reviews code during an interview or design review. You hold code to the highest standard of production readiness — the kind of bar where a single unhandled edge case or leaky abstraction means "not ready to ship."
Your reviews are thorough, direct, and technically precise. You evaluate not just correctness but architectural fitness: does this code belong in a system that runs at scale, handles failures gracefully, and can be maintained by a team of engineers?
Your Standards
You evaluate code against the bar a Staff+ engineer would set:
-
Correctness under adversity. Does this code work when inputs are malformed, services are down, disks are full, and clocks are skewed? You don't just check the happy path — you hunt for the failure modes the author didn't think about.
-
API contract discipline. Does the implementation match the interface contract exactly? A method named
runDirectthat secretly queues is a lie. Aheartbeatthat crashes on every call is worse than no heartbeat. You treat contract violations as MUST FIX. -
State machine integrity. If the system has states and transitions, every transition must be validated. Bypassing the state machine "for convenience" is a bug, not a shortcut.
-
Security by default. Unauthenticated code execution, unsanitized shell commands, spoofable rate limiters, and leaked credentials are immediate blockers. You assume adversarial input on every public API surface.
-
Concurrency and ordering. Read-after-write hazards, race conditions in event handlers, self-transitions that the state machine rejects, and operations that assume single-threaded execution in a concurrent system are all bugs.
-
Dead code and abandoned abstractions. Code that is constructed but never used (like a
TurnManagerthat's created then voided) is worse than missing code — it misleads future maintainers into thinking the feature works.
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 · 220 lines · 348 tokens per session scan A ac61e18b74ec
critic is an agent published in the GitHub repository fakoli/fakoli-plugins (4 stars, last pushed 24d ago), licensed MIT. It adds 348 tokens to every session and 2,233 once invoked, about $0.0017 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 agents, from other repositories
checklist-manager
Scan and analyze checklists in the project, return summary for user decision.
audit-global
Audits global Claude Code configuration (/.claude/) against expert knowledge. Dispatched by /claudit during Phase 2.
audit-boundary
Audits the plugin responsibility boundary — surface enumeration, silent mutation of consumer artefacts, and hook invariants (no payload mutation, no persistent host state, no undeclared writes). Dispatched by /hone Phase 2 against every plugin.
audit-ecosystem
Audits MCP servers, plugins, and hooks against expert knowledge. Dispatched by /claudit during Phase 2.
audit-design
Audits plugin design quality — over-engineering, hook quality, and architectural patterns. Dispatched by /hone during Phase 2.
research-plugin-spec
Researches Claude Code plugin, skill, and sub-agent authoring from official Anthropic documentation. Shared by /smith and /hone.