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-setupgit 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-setup)<a href="https://agentmods.dev/skills/get-tmonier/argot/argot-setup"><img src="https://agentmods.dev/badge/skills/get-tmonier/argot/argot-setup/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-setup"><img src="https://agentmods.dev/badge/skills/get-tmonier/argot/argot-setup.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 | $0.00129 | $0.05490 |
| Opus 5.5 | $0.00052 | $0.02196 |
| Sonnet 5.5 | $0.00026 | $0.01098 |
| Haiku 4.5 | $0.00013 | $0.00549 |
Grade A, and why
argot-setup 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 — 451 lines — stays where its author put it; the contents beside it link to each section on GitHub.
argot-setup
Argot learns how this repository writes code and flags what looks foreign to it. Everything downstream depends on one judgment: which code is the voice. Get that wrong and it fails silently — false alarms people learn to scroll past, or real problems never flagged. Neither looks like an error.
So this is not a wizard to click through. Every step below proposes something with the number that motivates it, and the user decides. Never apply an exclusion you cannot justify in one sentence.
Work through the phases in order. Any of them can be answered "skip".
0 · Preflight
argot --version. Missing → point at https://argot.tmonier.com/docs/getting-started/ and stop.- A git repository with real history. Argot has nothing to learn from a fresh
git init. - Default branch, clean tree. Fitting a feature branch bakes its unmerged commits into the voice; a dirty tree learns files as they sit on disk. Argot warns about both — relay the warning, never suppress it.
Say what setup will write: argot.toml and a committed .argot/ fit snapshot
(the learned voice, semantic index, detector artifacts, health and manifest),
plus whatever integrations get chosen in phase 8. Caches and one-run state stay
ignored. argot uninstall --dry-run lists everything
that would be removed, if they want to know the exit before the entrance.
1 · Proof before configuration
argot audit --format json > /tmp/argot-audit.json # keep it: phase 6 reads it
No configuration needed, exits 0, touches nothing. It fits the voice as it was ~50 commits ago in a temporary worktree and reports what would have met review since, attributed to the introducing commit. Show the card. This is the honest opener: here is what your own history says, before you change anything.
Say what it will cost before you start it, or they will kill it. Audit fits
the whole corpus once, so a large repository costs minutes and gigabytes, not
seconds — 924k lines of Object Pascal took 2 min 38 s and 3.6 GB. A narrower
--commits does not make it cheaper: the window only moves the base
commit, and the fit still reads every file. The lever is [exclude], which is
phase 2 — so on a repository this size, offer to do the obvious exclusions
first and audit second.
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 · 451 lines · 129 tokens per session scan A af00bbf26dea
argot-setup is a skill published in the GitHub repository get-tmonier/argot (51 stars, last pushed 20d ago), licensed MIT. It adds 129 tokens to every session and 5,490 once invoked, about $0.0005 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
release-habit-hooks
Cut a new release of the habit-hooks packages. Use when asked to release, publish, or bump the version. Reviews what lands, enforces the in-sync versioning rule, validates the changelog, and drives the tag-triggered PyPI publish.
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".
watch-pr
Watch a GitHub pull request for CI status, reviews, comments, merge conflicts, and terminal states using the gh-watch extension. Use when the user wants to monitor a PR, wait for CI, or track PR progress.
gh-find-prs
Survey open Codewhale PRs and triage each for mergeability and disposition against the real landing branch.
hunk-release
Prepares, publishes, verifies, and curates Hunk releases. Use for release metadata, benchmarks, tags, publishing, release videos, backports, or recovery.
github-pr-query
Query GitHub pull requests with jq filtering and reusable selectors.