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 get-tmonier/argot --skill argot-review-prgit clone --depth 1 https://github.com/get-tmonier/argotWrote 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/get-tmonier/argot/argot-review-pr)<a href="https://agentmods.dev/skills/get-tmonier/argot/argot-review-pr"><img src="https://agentmods.dev/badge/skills/get-tmonier/argot/argot-review-pr/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/get-tmonier/argot/argot-review-pr"><img src="https://agentmods.dev/badge/skills/get-tmonier/argot/argot-review-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 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 Excessive Agency · line 3 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.
- medium Excessive Agency · line 13 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 | $0.00078 | $0.02576 |
| Opus 5 | $0.00039 | $0.01288 |
| Sonnet 5 | $0.00016 | $0.00515 |
| Haiku 4.5 | $0.00008 | $0.00258 |
Grade A, and why
argot-review-pr 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
argot-review-pr
Score a pull request against the repo's committed local fit snapshot and report what fires — argot is statistical; false positives happen. Every hit names a rule, and the rule — not the confidence glyph — tells you what to recommend. The human decides what to do with the PR.
argot review scores the PR's diff without checking it out, using the reviewed
fit snapshot already committed in the local repository's .argot/, so it is
fast and leaves the working tree untouched. Before reviewing a PR, refresh that
snapshot locally from the intended accepted branch, review and commit it — never
fit the PR head and let the change certify itself.
Preconditions
argot --version— if missing, tell the user how to install it (see https://argot.tmonier.com/docs/getting-started/) and stop.- Run
argot status --format json. The snapshot must reportsnapshot.complete: trueandsnapshot.committed: true. If there is no initial fit, hand off to argot-setup; if artifacts are merely uncommitted, ask for their review and commit. For config incompatibility or a refresh recommendation, hand off to argot-refresh on the accepted branch. Never fit the PR head.watchremains usable and informational. - For a PR by number/URL, the
ghCLI must be authenticated and network access is required because argot fetches the PR diff through it. A locally availablebase..headrange or commit SHA needs no network; fetch the refs first if they are not local.
Run it
The target is a PR URL, #number / number, a base..head range, or a sha:
argot review 123 --format json
argot review https://github.com/org/repo/pull/123 --format json
argot review origin/main..my-branch --format json
Exit codes: 0 clean (or warn-severity hits only) · 1 at least one
error-severity hit · 2 setup/usage error. Treat 1 as "there is something
to raise in the review," not as a verdict on the PR.
Each hit in the JSON hits array carries rule (kebab-case name — branch on
this), rule_label, severity (error / warn — error hits drive exit 1),
confidence (unusual / suspicious / foreign — evidence strength,
display-grade only), evidence (the lines to show — the foreign symbol and
what the repo uses instead, or the duplicated function / intended area),
hash, and path / line_start / line_end. Read rule and severity,
not the raw score / threshold (those sit on different scales per signal).
In --format human the meta line identifies the source and rule. PR review
findings are evidence for review, not a claim that the PR or its author is
incorrect.
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 · 149 lines · 78 tokens per session scan A 5bed49613fb0
argot-review-pr is a skill published in the GitHub repository get-tmonier/argot (48 stars, last pushed yesterday), licensed MIT. It adds 78 tokens to every session and 2,576 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 2026-08-30.
Other skills, from other repositories
ph-philosophy-refinement
(PH) Use only when the user explicitly asks to change, review, or persist reusable development philosophy.
ph-ralplan
(PH) Use only when the user explicitly asks for an adversarial review of a high-risk delivery plan.
ph-review
(PH) Use to review a scoped implementation and report evidence-based findings before suggesting changes.
bellwether
Bring the current PR to a mergeable state: CI green, all review comments resolved, no merge conflicts. Self-contained — watches CI, fixes issues, watches again until merge-ready. Use when the user wants to keep a PR green, auto-fix CI, resolve review comments, or says "get this merged".
ai-debt-audit
Scan a repository for AI-generated technical, cognitive, and intent debt. Use when the user asks to audit a codebase for AI/vibe-coding risk, check for issues an AI coding assistant may have introduced (disabled RLS, hardcoded secrets, missing auth checks, SSTI, debug mode left on), assess technical debt after heavy…
repo-audit
Use when auditing a public repository for open-source readiness before publishing it.