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 wenhaochai/claude-plugins --skill reviewer-disciplinegit clone --depth 1 https://github.com/wenhaochai/claude-pluginsWrote 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/wenhaochai/claude-plugins/reviewer-discipline)<a href="https://agentmods.dev/skills/wenhaochai/claude-plugins/reviewer-discipline"><img src="https://agentmods.dev/badge/skills/wenhaochai/claude-plugins/reviewer-discipline/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/wenhaochai/claude-plugins/reviewer-discipline"><img src="https://agentmods.dev/badge/skills/wenhaochai/claude-plugins/reviewer-discipline.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 | $0.00084 | $0.00877 |
| Opus 5.5 | $0.00034 | $0.00351 |
| Sonnet 5.5 | $0.00017 | $0.00175 |
| Haiku 4.5 | $0.00008 | $0.00088 |
Grade A, and why
reviewer-discipline 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 1mo 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviewer Discipline
A filter, not a generator. Take a drafted weakness list and rewrite or drop every item that fails a check below. Apply it whether the paper is someone else's or your own.
The six CVPR reviewer errors
| Error | The check |
|---|---|
| Ignorance / inaccuracy | Every technical critique points at a specific line, equation, or table cell. |
| Pure opinion | "I dislike X" becomes "X violates principle Y because Z". |
| Novelty fallacy | Never reject for "lack of novelty" without citing the specific prior work; never accept for "novelty" without saying what is new against what. |
| Blank assertion | "This has been done before" carries a citation or it goes. |
| Policy entrepreneurism | Never invent a venue requirement. NeurIPS, ICML, ICLR, and TMLR do not require SOTA, a 70B run, or every baseline. |
| Intellectual laziness | Never reduce an evaluation to one metric. Non-SOTA accuracy with better efficiency, robustness, or interpretability still counts. |
Nine phrasings to refuse
Each one marks a lazy review. Never write:
- "The paper is good overall."
- "The work is okay but not outstanding."
- "Some experiments are missing", without naming which.
- "The writing could be improved", without naming where.
- "Related work is incomplete", without naming which papers.
- Any verdict that contradicts your own findings, such as "technically sound, but I recommend reject".
- "I have no further comments", after a substantial finding. A rebuttal update needs an explanation.
- "The contribution is limited", without naming which contribution and against what baseline.
- "The novelty is incremental", without saying what would qualify as non-incremental.
ARR specificity rewrite
Any drafted weakness matching the left column gets rewritten to the right form.
| Vague | Specific |
|---|---|
| "Missing relevant references" | "Missing references to [Smith et al. 2023] and [Jones 2024]" |
| "X is not clear" | "Y and Z are missing from the description of X" |
| "Formulation of X is wrong" | "Formulation of X misses the factor Y" |
| "Not novel" | "Highly similar work [citation], published at least three months prior" |
| "Missing recent baselines" | "Should compare against [Method X, Y, Z] from [citations]" |
| "Algorithm-dataset interaction is problematic" | "Using [decoding method] on [dataset] may lack the training data the n-best list needs" |
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.
- 1mo ago Changed · -43 tokens per session bcdf761cad12
- 1mo ago First seen · 68 lines · 127 tokens per session scan A b127be35557d
reviewer-discipline is a skill published in the GitHub repository wenhaochai/claude-plugins (18 stars, last pushed yesterday), licensed MIT. It adds 84 tokens to every session and 877 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-17.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…