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/hasithaishere/buildkite-developer-toolkit/buildkite-plugin-bootstrapnpx skills add hasithaishere/buildkite-developer-toolkit --skill buildkite-plugin-bootstrapgit clone --depth 1 https://github.com/hasithaishere/buildkite-developer-toolkitWhat 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 | $0.00076 | $0.01008 |
| Opus 5 | $0.00038 | $0.00504 |
| Sonnet 5 | $0.00015 | $0.00202 |
| Haiku 4.5 | $0.00008 | $0.00101 |
Grade A, and why
buildkite-plugin-bootstrap scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bootstrap a new Buildkite plugin
This skill generates a complete, ready-to-test Buildkite plugin repository so a developer goes from nothing to a passing test suite in one step.
How to run it
There is an executable scaffolder at scripts/scaffold.sh. Invoke it with the
plugin's short name (without the -buildkite-plugin suffix) and a style:
bash "${CLAUDE_SKILL_DIR}/scripts/scaffold.sh" <plugin-name> <bash|docker|go|container> [target-dir]
Examples:
bash "${CLAUDE_SKILL_DIR}/scripts/scaffold.sh" slack-notify bash ./slack-notify-buildkite-plugin
bash "${CLAUDE_SKILL_DIR}/scripts/scaffold.sh" run-in-docker docker
bash "${CLAUDE_SKILL_DIR}/scripts/scaffold.sh" metrics-reporter go
bash "${CLAUDE_SKILL_DIR}/scripts/scaffold.sh" test-report container
The four styles:
- bash — host-side hook + reusable
lib/plugin.bashhelpers. - docker — wrap the user's command in a container.
- go — compiled binary + downloader-shim hook + GoReleaser.
- container — package the plugin's own tool as a Docker image; the hook runs
it and passes agent creds in (Dockerfile +
bin/run+ wrapper).
If target-dir is omitted it defaults to <plugin-name>-buildkite-plugin in
the current directory. The script:
- creates the canonical layout (
plugin.yml,hooks/,tests/,.buildkite/,docker-compose.yml,README.md,LICENSE,.gitignore); - for
go, also emitsmain.go+main_test.go,go.mod, and.goreleaser.yml, plus a downloader-shimhooks/command; - for
container, also emits aDockerfileandbin/run, with a credential-passing wrapperhooks/command; - computes the correct
BUILDKITE_PLUGIN_<NAME>_*env-var prefix from the name and wires it into the hook/binary + tests so they match; - makes hook scripts executable;
- optionally runs
git init.
What to do after scaffolding
- Confirm the style. Bash = lightweight host-side hooks. Docker = wrap the
command in a container. Go = compiled binary with a downloader-shim hook, for
non-trivial logic that deserves real unit tests
(
reference/compiled-binary-plugins.md). Container = ship the plugin's own tool as a Docker image (reference/containerized-tool-plugins.md). If unsure, ask the developer. - Edit
plugin.ymlto declare the real settings (see thebuildkite-plugin-devskill,reference/plugin-yml-schema.md). KeepadditionalProperties: false. - Implement the hook logic in
hooks/. Read settings via the generated env-var prefix with safe:-defaults. - Write tests for each setting and the failure paths (see the
buildkite-plugin-testingskill). - Run locally:
docker-compose run --rm tests docker-compose run --rm lint - Verify current conventions. Buildkite plugin conventions occasionally change — before publishing, confirm against the live docs (see "Stay accurate" below).
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.
- 3d ago First seen · 91 lines · 76 tokens per session scan A 848864401b84
buildkite-plugin-bootstrap is a skill published in the GitHub repository hasithaishere/buildkite-developer-toolkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 1,008 once invoked, about $0.0004 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
ci-security-scanning-with-strix
Add security scanning to CI/CD with Strix — GitHub Actions, GitLab CI, or any pipeline — so every pull request gets a diff-scoped AI pentest that blocks vulnerable code before it merges, with results as PR comments and SARIF uploaded to code scanning. Covers both the self-hosted open-source CLI (runs in your runner)…
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
dsh-web-pre-push-checks
Use before pushing, opening or updating a pull request, or claiming dsh-web checks pass. Selects the required repository gates and diff-specific generation, build, and GUI evidence.
azsdk-common-pipeline-analysis
Analyze Azure SDK CI/CD pipeline failures into a structured diagnosis, and define the required output format. Load this skill before calling azsdkanalyzepipeline, which returns raw failure data that this skill interprets and formats. USE FOR: "pipeline failed", "build failure", "CI check failing", "tests failing in…
ci-formats-review
Review SARIF, CodeClimate, compact, markdown, badge, and other CI-facing output formats for correctness and integrator expectations. Use when changes affect machine-consumed report formats or CI presentation layers.
harness-setup
HAR: Project init, tool setup, agent config, memory setup, skill mirror sync. Trigger: setup, init, new project, CI/Codex setup, harness-mem, mirror. Do NOT load for: implementation, review, release, planning.