Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/get-tmonier/argotnpx agentmods add skills/get-tmonier/argot/argot-write-ruleWrote 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-write-rule)<a href="https://agentmods.dev/skills/get-tmonier/argot/argot-write-rule"><img src="https://agentmods.dev/badge/skills/get-tmonier/argot/argot-write-rule.svg" alt="Measured on agentmods" 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 | $0.00131 | $0.03476 |
| Opus 5 | $0.00066 | $0.01738 |
| Sonnet 5 | $0.00026 | $0.00695 |
| Haiku 4.5 | $0.00013 | $0.00348 |
Grade A, and why
argot-write-rule 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 8d 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 — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
argot-write-rule
argot's built-in rules cover patterns most repos eventually hit — foreign
imports, reinvented functions, layering breaks, gamed tests. Some conventions
are the repo's own: "route SQL through the query builder, never a
string-concatenated query," "HTTP calls go through the shared client, not a
bare one-off request," "retries always back off, never a hard-coded sleep
loop." For those, write a custom rule: a small rule.toml manifest plus a
sandboxed Rhai script under .argot/rules/<name>/,
committed with the rest of the repo. argot check discovers it fresh every
run — no recompiling argot. Its findings behave exactly like a built-in's:
same severities, same suppressions, same output formats, one more group,
custom. Full reference: https://argot.tmonier.com/docs/custom-rules/.
Rule authoring is a later, explicit workflow: use audit and ordinary checks to establish current behavior first. A custom rule must never turn a probabilistic finding into an unreviewed default gate. Writing or installing this skill does not schedule a check; a repository may choose to run its committed custom rules through an explicit local or CI workflow.
The gate: argot rules test <name> must be green
A custom rule is not done until its fixture suite is green. This is not polish at the end — it is the loop:
- Write fixtures before touching the script: at minimum one case that should fire and one that should stay silent. The silent case is what protects the team from a noisy rule — a rule that only ever proves it can fire has never been checked for false alarms.
- Run
argot rules test <name>with no script yet (or a stub) and watch it fail. - Write or fix
check.rhaiuntil every case passes. - Every time you touch the script afterward — while iterating, while
narrowing a false alarm, right before you hand it off — re-run
argot rules test <name>first. A script you haven't re-tested since your last edit is a script you don't know still works.
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.
- 8d ago First seen · 279 lines · 131 tokens per session scan A 1d99faf49685
argot-write-rule is a skill published in the GitHub repository get-tmonier/argot (48 stars, last pushed 5d ago), licensed MIT. It adds 131 tokens to every session and 3,476 once invoked, about $0.0007 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-review
(PH) Use to review a scoped implementation and report evidence-based findings before suggesting changes.
ph-ralplan
(PH) Use only when the user explicitly asks for an adversarial review of a high-risk delivery plan.
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.