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 instructions/buildkite/skills/agents-mdgit clone --depth 1 https://github.com/buildkite/skillsWrote 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/instructions/buildkite/skills/agents-md)<a href="https://agentmods.dev/instructions/buildkite/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/buildkite/skills/agents-md.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 | $0.00690 | $0.00690 |
| Opus 5 | $0.00345 | $0.00345 |
| Sonnet 5 | $0.00138 | $0.00138 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
skills AGENTS.md 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 3d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Buildkite Skills — Agent Context
A collection of AI agent skills that teach coding agents how to use Buildkite CI/CD.
Installed via npx skills add buildkite/skills or manually copied into agent skill directories.
Repository Structure
skills/ # All skills live here
buildkite-pipelines/ # Journey — pipeline YAML, step types, caching, parallelism
buildkite-migration/ # Journey — CI migration, bk pipeline convert, converting from GitHub Actions, Jenkins, CircleCI, Bitbucket, GitLab CI
buildkite-preflight/ # Cross-cutting — bk preflight against local uncommitted changes
buildkite-agent-runtime/ # Cross-cutting — buildkite-agent subcommands in job steps
buildkite-cli/ # Cross-cutting — bk CLI commands
buildkite-api/ # Cross-cutting — REST API, GraphQL, webhooks
Skill Architecture
Each skill directory contains:
SKILL.md(required) — core skill content, 10-18KB typicalreferences/(optional) — detailed content loaded on demandexamples/(optional) — complete runnable examplesagents/openai.yaml(required) — multi-agent platform metadataassets/(required) — icon and brand assets for agent marketplaces
Skills use progressive disclosure:
- Metadata (name + description) — always in context (~100 words)
- SKILL.md body — loaded when skill triggers (~1,500-2,500 words)
- Bundled resources — loaded as needed by the agent (unlimited)
Skills vs. Documentation
Skills are not documentation rewrites. They encode expertise — the judgment calls, defaults, and pitfalls that experienced Buildkite users know — rather than cataloguing features. Buildkite docs explain what's possible; skills teach agents how to do it correctly.
Assume the agent is already smart. Only include context it cannot infer on its own. Link to Buildkite docs for canonical reference; do not reproduce them.
Key Conventions
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.
- 3d ago First seen · 58 lines · 690 tokens per session scan A 48d9d5b4da8c
skills AGENTS.md is an instructions file published in the GitHub repository buildkite/skills (15 stars, last pushed 7d ago), licensed MIT. It adds 690 tokens to every session, about $0.0034 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 instructions, from other repositories
loom CLAUDE.md
Instructions for cosmix/loom, covering claude.md, project overview, build commands, architecture and source layout (loom/src/).
agentic-workflow CLAUDE.md
Instructions for gtrabanco/agentic-workflow, covering claude.md, repository layout, working rules, authoring a skill and hand off, don't compose across a model/effort boundary.
autovault CLAUDE.md
Instructions for autoworks-ai/autovault, covering claude.md, project, common commands, architecture and request flow.
claude-for-strategy CLAUDE.md
Instructions for daddia/claude-for-strategy, covering claude.md, layout, validation — run before opening a pr, 2. json sanity and 3. consulting reference mirrors.
agents-config CLAUDE.md
Claude Code instructions for artivilla/agents-config, covering agent config, commands, testing, key files and verification.
skills AGENTS.md
AGENTS.md instructions for DynamoDS/skills, covering claude.md, what this repo is, common commands, build the docs site (run from repo root) and validate a skill locally.