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 skills add kengo006/alexandria --skill criticgit clone --depth 1 https://github.com/kengo006/alexandriaWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kengo006/alexandria/critic)<a href="https://agentmods.dev/skills/kengo006/alexandria/critic"><img src="https://agentmods.dev/badge/skills/kengo006/alexandria/critic/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kengo006/alexandria/critic"><img src="https://agentmods.dev/badge/skills/kengo006/alexandria/critic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00079 | $0.00353 |
| Opus 5 | $0.00039 | $0.00177 |
| Sonnet 5 | $0.00016 | $0.00071 |
| Haiku 4.5 | $0.00008 | $0.00035 |
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 9d 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.
What it actually says
Critic (wrapper)
Authority lives in the master file — this wrapper only loads it. (Normal operation: the Writer spawns this role via integration/agents/critic.md.)
- Read
governance/role-division.md. - Read
roles/critic.md— red lines, blind-commitment order, three angles, report template.
Digest of red lines (master wins):
- Blind commitment first: write the evaluation standards and expected fatal flaw from the brief before reading the draft.
- Every criticism: location + concrete problem + one feasible repair direction. No content-free praise; no vague objections.
- Anti-sycophancy: raise by default; concede only for stated reasons; never soften a valid criticism.
- Citation-related criticisms are verified against the note or source first — never argued from impression.
- "No criticism", "my own uncertainties", and "negative universals" are mandatory report parts — each written even when the answer is "none", because a blank means none and did not look at once.
- Negative universals ("no one has", "the first", "the only"): name where each would break. For those sentences the scope/counterexample angle is not optional, regardless of the brief.
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.
- 9d ago First seen · 20 lines · 0 tokens per session scan A 5fda74d36b56
critic is a skill published in the GitHub repository kengo006/alexandria (5 stars, last pushed 16d ago), licensed MIT. It adds 79 tokens to every session and 353 once invoked, about $0.0004 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
asa-evidence-grounding-auditor
Use when auditing whether a skill decomposition is evidence-grounded, over-inference-safe, and publishable.
plannotator
Reference for using the Plannotator CLI: plan review, code review, annotating files, URLs, folders, and running local apps, annotating the last assistant message, browsing archived plan decisions, and exporting or sharing Guided Reviews. Invoke when asked to use Plannotator for anything not covered by a more specific…
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…
one-way-door
Flags irreversible decisions before commit. Use for data models, infra, auth boundaries, API contracts, event schemas, CI/CD.
review-r
Read-only R code review protocol for .R scripts. Checks code quality, reproducibility, domain correctness, tidyverse idioms, and professional standards; produces a report without editing. Use when user says "review this R script", "check the R code", "audit the analysis code", "code review on the R", or when an R file…