Borrowing it
Nothing to install: this file belongs to paullukic/coograph. 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/paullukic/coograph/main/.github/skills/coograph-ultra-review/SKILL.mdgit clone --depth 1 https://github.com/paullukic/coographWrote 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/paullukic/coograph/coograph-ultra-review)<a href="https://agentmods.dev/skills/paullukic/coograph/coograph-ultra-review"><img src="https://agentmods.dev/badge/skills/paullukic/coograph/coograph-ultra-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/paullukic/coograph/coograph-ultra-review"><img src="https://agentmods.dev/badge/skills/paullukic/coograph/coograph-ultra-review.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 | $0.00000 | $0.02127 |
| Opus 5.5 | $0.00000 | $0.00851 |
| Sonnet 5.5 | $0.00000 | $0.00425 |
| Haiku 4.5 | $0.00000 | $0.00213 |
Grade A, and why
coograph-ultra-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 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
coograph-ultra-review
/coograph-review is the everyday review: one reviewer, the working tree, minutes. This one is for a change that is big or dangerous enough that a single reader misses things: several hostile reviewers, each with one question in mind, every finding attacked by independent refuters before it reaches the report. It found, on one real stack, a lock released twice, a test that passed without its fix, and a queued job that could wipe a customer's files - each after an ordinary review had approved. It costs about a million tokens and twenty minutes per run. Optional, on purpose: suggest it, do not run it unasked.
Claude Code only (it runs as a saved workflow through the Workflow tool). In other tools, do the same by hand: one @Reviewer per dimension below, then a second pass that tries to refute each finding.
When to suggest it
Say that it exists - one sentence, with the cost - when the change in front of you is any of:
- more than about fifteen files, or a stack of several commits going to people for approval;
- queue jobs, cache claims, locks, retries, redelivery, timeouts, status transitions;
- anything that deletes, moves, overwrites or migrates data;
- a contract between two services or a client and a server;
- a plan for such a change, before the code exists (
planmode is the cheapest place to find a design hole).
Do not suggest it for a small, local change: /coograph-review is enough.
1. Pick the mode
| Mode | When | Reviewers | Lenses | Cost (measured) |
|---|---|---|---|---|
plan |
before writing code that touches lifecycle or concurrency | 2 on the session model, over the plan text and the code it names and its callers | 1 | 1.0–1.4M tokens, ~20 min |
full |
the first review of a PR or commit batch, and the one review of the whole PR once every fix is in (pr: N) |
4 on the session model, blast radius from the code graph | 2 (Opus, high effort) | 1.2–1.6M, 17–22 min; a 33-commit PR: 3.1M, 39 min |
delta |
a fix batch after a full run: are the previous findings fixed, and what did the changed lines break |
2 on Sonnet, no blast radius | 1 | ~0.5M, ~17 min |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 5e4c81970008
- 1mo ago First seen · 75 lines · 0 tokens per session scan A e27c3f4f4426
coograph-ultra-review is a skill published in the GitHub repository paullukic/coograph (17 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,127 tokens. 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 2026-09-26.
coograph-ultra-review compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| coograph-ultra-reviewpaullukic/coograph | Skill | 17 | 12d ago | MIT | A | 0 | Claude Code, Codex |
| generic-react-code-reviewertravisjneuman/.claude | Skill | 107 | yesterday | MIT | A | 71 | Claude Code, Codex |
| generic-fullstack-code-reviewertravisjneuman/.claude | Skill | 107 | yesterday | MIT | A | 64 | Claude Code, Codex |
| generic-static-code-reviewertravisjneuman/.claude | Skill | 107 | yesterday | MIT | A | 59 | Claude Code, Codex |
| agent-architecture-analysttravisjneuman/.claude | Skill | 107 | yesterday | MIT | A | 13 | Claude Code |
| generic-code-reviewertravisjneuman/.claude | Skill | 107 | yesterday | MIT | A | 70 | Claude Code, Codex |
| plan-review-architectureduthaho/claudekit | Skill | 97 | 3mo ago | MIT | A | 87 | Claude Code |