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 agentmods add skills/get-tmonier/argot/argot-refreshnpx skills add get-tmonier/argot --skill argot-refreshgit 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-refresh)<a href="https://agentmods.dev/skills/get-tmonier/argot/argot-refresh"><img src="https://agentmods.dev/badge/skills/get-tmonier/argot/argot-refresh.svg" alt="Measured on agentmods" 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 | $0.00136 | $0.02249 |
| Opus 5 | $0.00068 | $0.01125 |
| Sonnet 5 | $0.00027 | $0.00450 |
| Haiku 4.5 | $0.00014 | $0.00225 |
Grade A, and why
argot-refresh 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 6d 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Argot refresh
Treat a refresh like dependency maintenance, not a blind rebuild. The repository may have changed enough that its corpus scope, paths, and suppressions need review before the next fit freezes them into the shared snapshot.
Keep three concerns separate:
[exclude]and[detect]shape what the fit learns. Changing them requires a new fit.[rules],[[migration]], and mutes shape check policy. They do not train the model, but stale policy can hide useful findings and belongs in the same maintenance review..argot/is the generated, committed fit snapshot. CI only reads the base branch copy; it never fits or certifies a snapshot supplied by a PR.
Non-negotiable contract
- Work on the accepted/default branch with a clean source tree. If either is false, show the evidence and stop before fitting.
- If the repository has never been fitted, stop and hand off to argot-setup. Refresh maintains a reviewed baseline; it does not replace first-time corpus selection and setup verification.
- Never fit in CI, in the background, or merely because a commit count or age is high.
- Run every audit below read-only first. Do not edit
argot.toml, prune a mute, fit, stage, or commit while still assembling the proposal. - Ask for one explicit confirmation covering the proposed scope and mute changes. A user may accept some rows and reject others.
- Never remove an exclusion or standing mute just because it currently matches nothing; it may be a deliberate future guardrail. State the uncertainty.
- Never claim a hash mute on a still-present file is stale. Argot cannot recover its original hunk from the hash.
0 · Preflight
Run:
argot --version
git status --short
git branch --show-current
argot status --format json
If Argot is missing, stop and point to https://argot.tmonier.com/docs/getting-started/. Read these status fields:
snapshot.completeandsnapshot.committedrefresh.compatibilityrefresh.recommendation,score, andreasonsrefresh.next_actionrefresh.fit_shaandaccepted_sha
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.
- 6d ago First seen · 222 lines · 136 tokens per session scan A 27e0ef63592b
argot-refresh is a skill published in the GitHub repository get-tmonier/argot (48 stars, last pushed 3d ago), licensed MIT. It adds 136 tokens to every session and 2,249 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
cli-wiring
Bug class: Commands implemented in packages/squad-cli/src/cli/commands/ but never routed in cli-entry.ts.
debugging-workflows
Debug gh-aw workflows using run logs, audits, and failure triage.
debug-false-positive
Diagnose and fix a Fallow false positive or false negative through extraction, resolution, graph, analysis, reporting, and real-consumer verification.
triage-issue
Triage a GitHub issue against the current fallow codebase and determine validity, priority, scope, and likely implementation shape. Use when the user asks to triage an issue, assess a bug report, or evaluate an enhancement request.
lsp-review
Review fallow's LSP server behavior, diagnostics, code actions, code lens, and protocol-facing UX. Use when changes touch crates/lsp or LSP-visible behavior.
recipe-diagnose
Investigate problem, verify findings, and derive solutions.