Borrowing it
Nothing to install: this file belongs to Cotal-AI/Cotal. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Cotal-AI/Cotal/main/.claude/skills/cold-review/SKILL.mdgit clone --depth 1 https://github.com/Cotal-AI/CotalWrote 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/cotal-ai/cotal/cold-review)<a href="https://agentmods.dev/skills/cotal-ai/cotal/cold-review"><img src="https://agentmods.dev/badge/skills/cotal-ai/cotal/cold-review/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/cotal-ai/cotal/cold-review"><img src="https://agentmods.dev/badge/skills/cotal-ai/cotal/cold-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Excessive Agency · line 232 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00119 | $0.03777 |
| Opus 5 | $0.00060 | $0.01888 |
| Sonnet 5 | $0.00024 | $0.00755 |
| Haiku 4.5 | $0.00012 | $0.00378 |
Grade A, and why
cold-review 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 11d 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 — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cold review
A cold reviewer is not an extra panelist. It is a control on the panel.
A panel converges. Reviewers read each other, findings get confirmed by seats already looking in the same direction, and the group arrives somewhere with more confidence than any member earned alone. That convergence is usually right, which is why it is dangerous when it is wrong: a panel of three has approved a head carrying a defect all three missed, and what surfaced it was a differently framed read, not a fourth verifier.
This file is read by the person who WRITES the brief, not by the seat being briefed. The value is in the brief, not in the seat's context. A cold seat that never loaded a skill file, never joined the mesh and received nothing but a persona has produced three blockers that two fully-briefed lenses missed. So nothing here requires the graded seat to have access to this document, and no rule below may be written so that it does.
The isolation
- Never joins the review channel. Not muted, not quiet. Not joined.
- Never shown the panel's findings, verdict, or round count, including as a list of things already ruled out so it can skip them. Skipping-instructions are findings shaped like scope.
- DM-only or file-only input from the author or manager. Its verdict goes first-hand to the dedicated record destination itself.
- Never shares a model family with whoever WROTE the change.
Why never join, stated correctly. Joining exposes the seat to the panel's live traffic for as
long as it is subscribed, and the panel is active during a cold read. Replay of history is a second
exposure path but not a guaranteed one: replay is channel.replay ?? defaults.replay ?? true, a
default-true policy with a per-channel override, so a replay=false channel would not replay. The
rule does not depend on that setting in either direction, and a brief that justifies it by replay
alone is resting on a config it cannot rely on.
Prefer the ACL to the request. subscribe: [] plus an allowSubscribe that excludes the panel
channel makes non-join a property of the seat rather than an instruction it must follow. Where a
fence exists, use the fence.
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.
- 11d ago First seen · 258 lines · 119 tokens per session scan A d18996604dbe
cold-review is a skill published in the GitHub repository Cotal-AI/Cotal (274 stars, last pushed today), licensed Apache-2.0. It adds 119 tokens to every session and 3,777 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
Frontend Standards
Complete JavaScript, CSS, accessibility, event architecture, bundle pipeline, and admin UI coding standards.
gh-find-prs
Survey open Codewhale PRs and triage each for mergeability and disposition against the real landing branch.
improve
Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.
code-review-patterns
Multi-dimensional code assessment across security, quality, performance, and maintainability with confidence-gated reporting (>=80%) and Router Contract generation.
code-review-pipeline
Multi-dimensional code review across correctness, security, performance, and maintainability with confidence-gated reporting and remediation loops.
subagent-driven-development
Use when executing implementation plans with independent tasks in the current session. Dispatches fresh subagent per task.