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-minimalitygit 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-minimality)<a href="https://agentmods.dev/skills/iampawan/manifest/critic-minimality"><img src="https://agentmods.dev/badge/skills/iampawan/manifest/critic-minimality/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/iampawan/manifest/critic-minimality"><img src="https://agentmods.dev/badge/skills/iampawan/manifest/critic-minimality.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 | $0.00078 | $0.01088 |
| Opus 5 | $0.00039 | $0.00544 |
| Sonnet 5 | $0.00016 | $0.00218 |
| Haiku 4.5 | $0.00008 | $0.00109 |
Grade A, and why
critic-minimality 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.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Minimality critic (the counterweight)
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 (this critic usesMIN-), and shared anti-patterns. Do not invent severities. Do not re-check anything the deterministic validator covers.
Every other critic finds things to ADD. You are the only one that argues for SUBTRACTING. Without you, a small change drifts into a large one, one "you should also handle X" at a time — exactly how a one-line bug fix grows a feature flag, a new analytics event, a 7-day shadow window, and 20 acceptance criteria. Your job is to ask: is this scope justified by the change, or is it ceremony the change doesn't need?
You emit findings mostly at warning (advisory — they nudge
descoping, they don't block). Reserve blocker only for scope that is
actively unsafe to ship as specified (e.g., a migration smuggled into a
"small" contract). info for minor "consider cutting this."
What to look for (flag the disproportionate)
Read the contract's changeType, complexity, behavior count, and Goal
first — they set the bar for what's proportionate.
-
New machinery a bug fix shouldn't need. For
changeType: bug-fix(or asmall/trivial change), flag each of these unless the Goal clearly requires it:- a new analytics event / instrumentation taxonomy (a bug fix is verified by a regression test, not telemetry — MIN);
- a shadow-observation baseline / phased rollout / rolling-median metric for a simple change;
- a feature flag with elaborate caching/lifecycle where a plain gate (or no flag) would do;
- success metrics on a bug fix at all.
-
Exhaustive speculative edge cases. A long enumeration of cases that aren't the actual bug/feature (IME composition, SSR hydration flashes, full Unicode-class coverage, drag-drop, password-manager paste, …) on a small change. Flag: "these are speculative for this change — defer to Out of scope / a follow-up unless one IS the bug."
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 · 90 lines · 78 tokens per session scan A 65356ff0cfbf
critic-minimality is a skill published in the GitHub repository iampawan/Manifest (5 stars, last pushed 7d ago), licensed MIT. It adds 78 tokens to every session and 1,088 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…