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 mthines/agent-skills --skill criticalgit clone --depth 1 https://github.com/mthines/agent-skillsWrote 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/mthines/agent-skills/critical)<a href="https://agentmods.dev/skills/mthines/agent-skills/critical"><img src="https://agentmods.dev/badge/skills/mthines/agent-skills/critical.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 119 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 139 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 156 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 243 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00165 | $0.03136 |
| Opus 5 | $0.00082 | $0.01568 |
| Sonnet 5 | $0.00033 | $0.00627 |
| Haiku 4.5 | $0.00016 | $0.00314 |
Grade A, and why
critical 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 7d 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 — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Critical — Adversarial Pre-Mortem
Challenge the proposed work as a hostile staff engineer would.
Surface specific, grounded failure modes; force at least one steelmanned alternative; hand scoring to /confidence.
Why this exists, in one paragraph. A single LLM "be honest" pass tends to confirm rather than challenge — naïve self-refine has been shown to amplify bias (Pride and Prejudice, ACL 2024) and to add no gains over self-consistency when the initial answer is already strong (SELF-[IN]CORRECT, AAAI). External grounding plus a fixed taxonomy beats vague introspection (CRITIC framework). This skill is the structured counter-pressure: one pass, hostile persona, mandatory citations, mandatory steelman, no self-scoring.
Contents
- When to use
- Mode detection
- The persona contract
- External grounding rule
- Taxonomy —
planmode - Taxonomy —
codemode - Taxonomy —
analysismode - Mandatory steelman alternative
- Output format
- Composition with other skills
- Hard rules and non-goals
When to use
| Use it | Don't use it |
|---|---|
| Before locking a plan or handing off to autonomous execution | On routine, low-stakes edits (typos, doc tweaks, trivial refactors) |
| When the user says "I'm in doubt", "challenge this", "is this really right" | After /confidence already passed at ≥ 90% with zero concerns |
| Right before a high-stakes PR (migrations, auth, billing, shared infra) | As a reflex on every change — the cost outweighs the value |
| Mid bug investigation when the proposed root cause feels off | When you only need a syntactic check — /code-quality covers that |
Slash form: /critical [plan|code|analysis] |
When iteration is desired — this skill is single-pass by design |
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.
- 7d ago First seen · 266 lines · 165 tokens per session scan A c0b037b3558c
critical is a skill published in the GitHub repository mthines/agent-skills (12 stars, last pushed 2d ago), licensed MIT. It adds 165 tokens to every session and 3,136 once invoked, about $0.0008 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
code-review-and-quality
Runs code review as a change-management process — right-sizing the diff, labeling findings by required-vs-optional severity, applying structural remedies for complexity, and resolving reviewer/author disagreements. Use when a change needs splitting before review, when review comments need severity labels, when a…
coding-standards
Cross-language code-quality heuristics -- function size, nesting depth, magic numbers, comment intent, naming -- for reviewing or writing code in any language. Use when reviewing code for maintainability, setting up lint rules, or onboarding conventions. For Go-specific idioms use go-service-idioms, for API contracts…
doubt-driven-development
Subjects a non-trivial decision to a fresh-context adversarial review before it stands, in-flight rather than as a post-hoc PR verdict. Use before an architectural decision under uncertainty, before committing non-trivial code, before asserting a non-obvious fact ("this is safe", "this scales", "this matches the…
best-practices
Apply modern web development best practices for security, compatibility, and code quality. Use when asked to "apply best practices", "security audit", "modernize code", "code quality review", or "check for vulnerabilities".
code-reviewer
Runs a fixed-category severity scan over a diff, file, or snippet — correctness, security, error handling, concurrency, performance, readability, tests — and emits a CRITICAL/HIGH/MEDIUM/LOW/INFO-graded report. Use when asked to "scan this code", grade a change by severity, or review Go code for concurrency bugs (data…
code-simplification
Simplifies working code for clarity without changing behavior — reduces nesting, renames vague identifiers, removes dead code and unnecessary abstraction. Use when code works but is harder to read, maintain, or extend than it should be, or when a review flagged accumulated complexity. Not for adding features or fixing…