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-checkgit 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-check)<a href="https://agentmods.dev/skills/get-tmonier/argot/argot-check"><img src="https://agentmods.dev/badge/skills/get-tmonier/argot/argot-check/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-check"><img src="https://agentmods.dev/badge/skills/get-tmonier/argot/argot-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00110 | $0.03467 |
| Opus 5.5 | $0.00044 | $0.01387 |
| Sonnet 5.5 | $0.00022 | $0.00693 |
| Haiku 4.5 | $0.00011 | $0.00347 |
Grade A, and why
argot-check 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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
argot-check
Run argot on the current changes and act on what it reports. argot is
statistical; false positives happen. Every hit names a rule, and the rule —
not the confidence glyph — tells you what to do. The human has the last word.
Preconditions
argot --version— if missing, tell the user how to install it (see https://argot.tmonier.com/docs/getting-started/) and stop.- The repo must have a complete fit snapshot. Run
argot status --format json: it must reportsnapshot.complete: true. If there is no initial fit, hand off to argot-setup. If it reports uncommitted files, ask the user to review and commit the listed.argot/artifacts; if refresh isrecommended/strongly_recommended, or config is incompatible, hand off to argot-refresh. It readsrefresh.next_action, reviews scope and mutes, then fits locally only after confirmation.watchis informational. Never fit automatically during a routine check.
Run it
Score the changes you care about, as JSON:
argot check --format json # working-tree changes
argot check --staged --format json # what's about to be committed
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 act on," not as a mystery failure — walk the decision tree below.
Each hit in the JSON hits array carries:
| Field | Use |
|---|---|
rule |
Kebab-case rule name (foreign-import, redundant, …) — branch on this (see the rules table and decision tree). |
rule_label |
Human label of the rule: foreign import, already implemented here, … |
severity |
error or warn — the rule's configured severity for this run. Error hits drive exit code 1. |
confidence |
unusual / suspicious / foreign — strength of the evidence, display-grade only (see below). |
evidence |
The lines to show the user — names the foreign symbol, the duplicated function, or the area the code belongs in. |
hash |
Stable id for argot mute <hash>. |
path, line_start, line_end |
Where it is. |
source |
workdir / staged / untracked / a commit SHA — where the change came from. |
score, threshold |
Raw internals. Read rule and severity, not these — they sit on different scales per signal, so comparing them directly is meaningless. |
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 First seen · 223 lines · 110 tokens per session scan A 2076b22b474a
argot-check is a skill published in the GitHub repository get-tmonier/argot (51 stars, last pushed 22d ago), licensed MIT. It adds 110 tokens to every session and 3,467 once invoked, about $0.0004 per session on Opus 5.5. 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
cejel-scan
Score a repository's engineering-trust signals with Cejel and read the resulting certificate. Use when the user asks how trustworthy, well-tested, or production-ready a codebase is, wants a trust score, certificate, or badge for a repository, asks whether AI-written code is backed by tests and CI, or wants to compare…
review-work
Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.
deploy
Use when ready to ship — runs pre-push gates (lint, typecheck, build, tests, security sweep), commits, releases, and pushes. Standalone, never auto-invoked. Push always requires explicit confirmation. Trigger with /hyperflow:deploy, "ship it", "ready to push", "release", "cut a release", "deploy".
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
brooks-test
Test quality review drawing on twelve classic engineering books — with primary focus on xUnit Test Patterns, The Art of Unit Testing, How Google Tests Software, and Working Effectively with Legacy Code — that diagnoses structural problems in an existing test suite: brittleness, mock abuse, coverage illusions, slow…
include-test-files-that-assert-on-behavior-being-changed-in-decl
When delegating a task affected by this skill, include.