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 chankov/agent-fleet --skill repository-ai-setupgit clone --depth 1 https://github.com/chankov/agent-fleetWrote 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/chankov/agent-fleet/repository-ai-setup)<a href="https://agentmods.dev/skills/chankov/agent-fleet/repository-ai-setup"><img src="https://agentmods.dev/badge/skills/chankov/agent-fleet/repository-ai-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/chankov/agent-fleet/repository-ai-setup"><img src="https://agentmods.dev/badge/skills/chankov/agent-fleet/repository-ai-setup.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 | $0.00060 | $0.01397 |
| Opus 5.5 | $0.00024 | $0.00559 |
| Sonnet 5.5 | $0.00012 | $0.00279 |
| Haiku 4.5 | $0.00006 | $0.00140 |
Grade A, and why
repository-ai-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 20d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository AI Setup
Initial and repeated setup of a target repository's .ai/rules, .ai/commands,
and .ai/agent-prompts from the Fleet catalogue, plus the Fleet settings handoff
that makes the result load automatically. Follow
references/setup-flow.md for the phase checklists,
references/apply-contract.md for the deterministic write rules, and
references/provenance-template.md for the file metadata contract.
When to Use
Apply this skill when the user invokes /af-setup-rules (optionally with a
free-text change request such as "add API compatibility rules"), or asks to set
up, review, or extend a repository's AI rules from the Fleet catalogue.
When NOT to use:
- Ordinary planning, building, or reviewing — read the already-installed
.ai/rulesindex instead of re-running setup. - Deterministic installation (
agent-fleet setup) — that path stays non-interactive and never runs this interview. - Editing Fleet settings by hand or via any path other than the CLI below.
Non-negotiable boundaries
- Catalogue source is the installed Fleet npm package only. Resolve it with
requirePackageCatalogue(packageRoot)frombin/lib/project-provenance.jsbefore any selection. If the package has nocatalog/payload, stop this capability with a clear error — other Fleet functionality keeps working. Never copy the catalogue beneath.pi/, never infer one from a source checkout, never download it silently. This skill consumes the library; the library is not part of any repository's own policy. - Missing rules/docs paths warn and continue, never fail setup. A configured root that does not exist on disk is advisory, not fatal.
- This skill never edits overrides and contains no overrides merge
algorithm. All settings changes go through the deterministic CLI:
preview with
agent-fleet configure --rules <dirs> --docs <paths> --dry-run, then apply the reviewed preview with--expect-hash <expectedHash> --yes. There is no second Markdown merge writer in this skill or its references. - Provenance is the single sidecar
.ai/agent-fleet-ai-state.json. Read, classify, and write it only viabin/lib/project-provenance.js(readProjectProvenance,classifyProjectFile,applyAcceptedProjectFiles). Template-derived files carryfleet-template/fleet-source-versionfrontmatter; repo-derived files never get an invented template identity.appliedHashlives in the sidecar, never in the hashed file. The sidecar is preserved on uninstall and is not installer ownership. - Existing explicit policy is preserved without redundant confirmation. A rule inferred only from code frequency or consistency is a proposal with cited evidence — never normative — until the user explicitly accepts it.
What ships with it
5 files 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.
- 20d ago First seen · 118 lines · 60 tokens per session scan A faee1aec8067
repository-ai-setup is a skill published in the GitHub repository chankov/agent-fleet (19 stars, last pushed yesterday), licensed MIT. It adds 60 tokens to every session and 1,397 once invoked, about $0.0002 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 2026-09-27.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…