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 iampawan/Manifest --skill critic-regressiongit clone --depth 1 https://github.com/iampawan/ManifestWrote 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/iampawan/manifest/critic-regression)<a href="https://agentmods.dev/skills/iampawan/manifest/critic-regression"><img src="https://agentmods.dev/badge/skills/iampawan/manifest/critic-regression.svg" alt="Measured on agentmods" 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 | $0.00070 | $0.03068 |
| Opus 5 | $0.00035 | $0.01534 |
| Sonnet 5 | $0.00014 | $0.00614 |
| Haiku 4.5 | $0.00007 | $0.00307 |
Grade A, and why
critic-regression 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 8d 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 — 340 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Regression critic
Protocol: Follow
reference/CRITIC-RULES.md(the compact runtime rules) at the plugin root for severity definitions (the closed enum blocker/warning/info), the output JSON schema, ID prefixes, and shared anti-patterns. This skill defines only WHAT to look for. Do not invent severities like "high"/"medium" — the validator rejects them. Do not re-check anything the deterministic validator (scripts/validate.mjs) already covers; add the judgment layer on top.
You read the existing codebase — across every repo this team owns that the contract might touch — and flag anything in the new contract that might break, conflict with, or require coordination with shipped code. The other critics treat the contract in isolation; you're the one who knows the rest of the system exists.
Inputs
The contract, plus a repo configuration that tells you what to scan.
Repo configuration
Look for .manifest/repos.yml in the current working directory. It has
this shape:
repos:
- name: web
github: your-org/web-app # preferred — read via GitHub MCP
path: ~/work/web-app # optional — local clone for speed
platforms: [web]
languages: [typescript, tsx]
eventSdk: amplitude
testPattern: "cypress/**/*.cy.ts"
- name: flutter
github: your-org/mobile-app
platforms: [ios, android]
languages: [dart]
eventSdk: firebase
testPattern: "integration_test/**/*_test.dart"
- name: backend
github: your-org/backend-api
platforms: [server]
languages: [typescript, python]
eventSdk: amplitude-node
testPattern: "tests/**/*.test.ts"
routePattern: "src/routes/**/*.ts"
Each repo entry needs either github (org/repo identifier) or path
(local clone). If both are present, prefer github — it's always
current with the default branch. Local path is a perf-only fallback.
If .manifest/repos.yml is missing, fall back to scanning only the
current repo via local tools.
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.
- 8d ago First seen · 340 lines · 70 tokens per session scan A ebc8a3220a99
critic-regression is a skill published in the GitHub repository iampawan/Manifest (5 stars, last pushed 6d ago), licensed MIT. It adds 70 tokens to every session and 3,068 once invoked, about $0.0003 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
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
gsd-ns-review
Route to the appropriate quality / review skill based on the user's intent. gsd-code-review-fix was absorbed by gsd-code-review --fix in #2790.
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…
gitnexus
A code-graph analysis add-on for examining an existing codebase, including symbols, call paths, execution flows, and effects across repositories. It can query GitNexus through its command-line or MCP interfaces.
cleanup-code-inspections
Reduce technical debt and improve code quality by systematically resolving static analysis warnings.
superlint
This skill describes the mandatory standard operating procedure for using our internal SuperLint tool. Use this when tasks require fixing code quality issues according to corporate standards.