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-setup-cigit 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-ci)<a href="https://agentmods.dev/skills/get-tmonier/argot/argot-setup-ci"><img src="https://agentmods.dev/badge/skills/get-tmonier/argot/argot-setup-ci/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-ci"><img src="https://agentmods.dev/badge/skills/get-tmonier/argot/argot-setup-ci.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 | $0.00094 | $0.01556 |
| Opus 5.5 | $0.00038 | $0.00622 |
| Sonnet 5.5 | $0.00019 | $0.00311 |
| Haiku 4.5 | $0.00009 | $0.00156 |
Grade A, and why
argot-setup-ci 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
argot-setup-ci
Add argot to a repository's CI as a non-blocking pattern check on every pull request. Never make it block the merge unless the user explicitly asks for a gate. This is user-wired automation: the Action runs only at the GitHub event in the workflow the repository commits; it does not install or claim an agent end-of-turn or acceptance lifecycle.
The Action installs Argot but never fits in CI. CI and local setup are one
decision: a committed argot.toml plus a complete committed .argot/ fit
snapshot already on the PR base/default branch — the excludes and learned
detector data that keep every check reproducible. A repository without that
snapshot must run the full
argot-setup flow first. The excludes
that keep vendored, generated and demo trees out of the voice — makes the CI
voice sharper, and argot is only as good as that scoping. If the repository
has no argot.toml yet, offer the full argot-setup
flow first, which covers CI as one of its phases. Come here when the user
wants CI specifically, or already has a configured repo.
Steps
-
Confirm the repo is on GitHub. (Forks: enable Actions in Settings first.)
-
Check the bootstrap boundary before writing a workflow. On the branch that future pull requests will target (normally the default branch),
argot status --format jsonmust showsnapshot.complete: trueandsnapshot.committed: true. Verify the tracked artifact is available from that branch, for example:git show HEAD:.argot/scorer-config.json > /dev/nullA snapshot committed only in the PR adding the workflow does not satisfy this: the Action reads the PR base so a change cannot certify itself. If it is absent, finish, review, commit, and merge the baseline first; add CI in a follow-up PR or commit. Do not use CI fitting as a workaround.
-
Write
.github/workflows/argot.yml:name: argot on: pull_request: push: branches: [main] permissions: contents: read pull-requests: write # the sticky score comment security-events: write # SARIF code-scanning annotations jobs: voice: runs-on: ubuntu-latest steps: - uses: actions/checkout@v4 with: fetch-depth: 0 # Action reads the committed snapshot from the PR base - uses: get-tmonier/argot@main
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 · 132 lines · 94 tokens per session scan A 5f22aacff44c
argot-setup-ci is a skill published in the GitHub repository get-tmonier/argot (51 stars, last pushed 22d ago), licensed MIT. It adds 94 tokens to every session and 1,556 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
setup
Guided onboarding for nullius in this repo — detects test frameworks to propose Oracle config, offers the GitHub Action CI check, and walks through enabling the hook plugin. Use when a user asks to set up, install, enable, configure, or onboard nullius, or asks what nullius needs to be fully working here.
cli-audit-review
Scored MR/PR/diff review skill calibrated for strict infrastructure and automation changes. Use for merge-request reviews, pull-request reviews, scored reviewer gates, convention compliance, Ansible roles/collections, Molecule, GitLab CI, semantic-release, packaging, Go/Cobra CLIs, PowerShell, shell/Python helpers…
Code Coverage Analysis
Measure and enforce test coverage with Istanbul/nyc, c8, Jest, and Vitest. Covers branch versus line coverage, per-directory thresholds, CI gates, and correctly excluding generated code from reports.
tech-debt-ci-review
Codex adapter for deep technical-debt and CI-stability audits. Use when asked to find test theater, flaky tests, missing or mis-scoped tests, brittle CI/toolchain behavior, structural debt blocking green PRs, or a remediation order for opencode-swarm.
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.
habit-hooks-review
Spawn a reviewer sub-agent to assess a change set against habit-hooks's coding principles. Use AFTER habit-hooks reports clean — habit-hooks catches structural smells; this catches what it cannot (correctness, tests, design, missed edge cases).