Borrowing it
Nothing to install: this file belongs to berntpopp/genefoundry-router. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/berntpopp/genefoundry-router/main/.claude/skills/fleet-drift-conformance/SKILL.mdgit clone --depth 1 https://github.com/berntpopp/genefoundry-routerWrote 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/berntpopp/genefoundry-router/fleet-drift-conformance)<a href="https://agentmods.dev/skills/berntpopp/genefoundry-router/fleet-drift-conformance"><img src="https://agentmods.dev/badge/skills/berntpopp/genefoundry-router/fleet-drift-conformance/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/berntpopp/genefoundry-router/fleet-drift-conformance"><img src="https://agentmods.dev/badge/skills/berntpopp/genefoundry-router/fleet-drift-conformance.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00040 | $0.00396 |
| Opus 5 | $0.00020 | $0.00198 |
| Sonnet 5 | $0.00008 | $0.00079 |
| Haiku 4.5 | $0.00004 | $0.00040 |
Grade A, and why
fleet-drift-conformance 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 10d 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.
What it actually says
Fleet Drift & Conformance
Follow AGENTS.md first. These tools catch two failure classes CI alone misses: prod divergence (a backend green in CI but dead / renamed in prod) and tool poisoning / rug-pull (a tool definition changing after approval).
Tools
make fleet-probe— live-probe every enabled backend for reachability + a non-zero tool harvest; fails loud on 0-tool or unreachable backends. Run before trusting/health.genefoundry-router drift(drift.py) — fingerprint each tool definition and diff a live snapshot against the pinned fleet manifest; exits non-zero for CI/cron.make conformance— MCP Transport & Session Standard v1 probe (single stateless/mcp, no 307, canonicalserverInfo/ health).make snapshot-fleet/make snapshot-catalog/make snapshot-baseline— regenerate the fleet manifest, discovery catalog, and pinned drift baseline.
Workflow
- Reproduce with
make fleet-probe(ordrift/conformance) and read the diff. - If the change is legitimate (a backend intentionally changed tools), review it, then re-pin:
make snapshot-baseline/ regenerate the catalog. - If unexpected, treat it as a possible rug-pull — investigate the backend before re-pinning.
- Keep the guard / snapshot tests green; run
make ci-local.
Common mistakes
- Re-pinning the baseline to make drift "pass" without reviewing why it changed.
- Trusting a url-is-configured
/healthinstead of a live harvest.
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.
- 10d ago First seen · 28 lines · 40 tokens per session scan A 77c4773c743f
fleet-drift-conformance is a skill published in the GitHub repository berntpopp/genefoundry-router (4 stars, last pushed 4d ago), licensed MIT. It adds 40 tokens to every session and 396 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
experimental-code-coverage-local-debugger
Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.
work
Deliver one maintainer-approved EmDash issue, choosing the bug-fix path for a defect and the direct implementation path for an enhancement or task.
ios-simulator
Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.