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-devnpx skills add hasithaishere/buildkite-developer-toolkit --skill buildkite-plugin-devgit 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 | $0.00120 | $0.02140 |
| Opus 5 | $0.00060 | $0.01070 |
| Sonnet 5 | $0.00024 | $0.00428 |
| Haiku 4.5 | $0.00012 | $0.00214 |
Grade A, and why
buildkite-plugin-dev 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 yesterday.
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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Buildkite Plugin Development
You are an expert engineer building production-grade custom Buildkite plugins. A Buildkite plugin is a small git repository the agent clones and runs at specific points in a build via hook scripts. Follow these rules exactly — they reflect how the Buildkite agent actually loads and runs plugins.
Official docs (verify specifics here; some details evolve):
- Writing plugins: https://buildkite.com/docs/pipelines/integrations/plugins/writing
- Using plugins: https://buildkite.com/docs/pipelines/integrations/plugins/using
- Plugin tools/index: https://buildkite.com/docs/pipelines/integrations/plugins
- Agent hooks: https://buildkite.com/docs/agent/v3/hooks
Non-negotiable rules
- Repo naming. Public plugin repos are conventionally named
<thing>-buildkite-plugin(e.g.docker-buildkite-plugin). The agent resolvesmy-org/docker#v1.0.0togithub.com/my-org/docker-buildkite-plugin. - Every plugin has a
plugin.ymlat the repo root describing its name, author, requirements, and a JSON-Schemaconfigurationblock. Seereference/plugin-yml-schema.md. - Hooks live in
hooks/as executable scripts. Each hook file is named after the lifecycle event (environment,command,pre-exit, ...) with no extension, must bechmod +x, and must start with a shebang. Seereference/hooks.mdfor the full list and execution order. - Every hook script starts with:
(or#!/bin/bash set -euo pipefail#!/usr/bin/env bash). This catches unset vars and pipe failures early. - Read config from environment variables, never by parsing YAML. The agent
converts the user's
plugins:YAML into env vars. Seereference/env-var-mapping.mdfor the exact naming algorithm (uppercasing, non-alphanumeric →_, array indices_0,_1, ...). - Always read with a safe default:
"${BUILDKITE_PLUGIN_MYPLUGIN_TIMEOUT:-10}". Never assume a var is set. - Always quote variable expansions (
"$VAR") and use[[ ... ]]for tests. Runshellcheckon every hook. - Ship tests. Every plugin needs Bats tests and a CI pipeline. Delegate
the test mechanics to the
buildkite-plugin-testingskill, but never call a plugin "done" withouttests/and.buildkite/pipeline.yml.
What ships with it
36 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.
- reference/advanced-plugin-yml.md 4.4 KB
- reference/auth-and-registry-plugins.md 4.2 KB
- reference/bash-plugin-structure.md 4.3 KB
- reference/building-commands.md 3.0 KB
- reference/buildkite-agent-cli.md 3.1 KB
- reference/compiled-binary-plugins.md 4.6 KB
- reference/containerized-tool-plugins.md 3.2 KB
- reference/env-var-mapping.md 3.1 KB
- reference/hooks.md 3.4 KB
- reference/plugin-yml-schema.md 2.1 KB
- reference/stateful-and-backend-plugins.md 4.6 KB
- templates/bash-plugin/.buildkite/pipeline.yml 506 B
- templates/bash-plugin/docker-compose.yml 391 B
- templates/bash-plugin/hooks/command 1.0 KB
- templates/bash-plugin/lib/plugin.bash 2.4 KB runs code
- templates/bash-plugin/plugin.yml 535 B
- templates/bash-plugin/tests/command.bats 1.1 KB
- templates/bash-plugin/tests/plugin.bash.bats 1.6 KB
- templates/containerized-tool-plugin/.buildkite/pipeline.yml 535 B
- templates/containerized-tool-plugin/bin/run 834 B
- templates/containerized-tool-plugin/docker-compose.yml 232 B
- templates/containerized-tool-plugin/Dockerfile 844 B
- templates/containerized-tool-plugin/hooks/command 1.7 KB
- templates/containerized-tool-plugin/plugin.yml 721 B
- templates/containerized-tool-plugin/tests/command.bats 1.6 KB
- templates/docker-plugin/docker-compose.yml 233 B
- templates/docker-plugin/hooks/command 1.7 KB
- templates/docker-plugin/plugin.yml 988 B
- templates/docker-plugin/tests/command.bats 2.1 KB
- templates/go-plugin/.goreleaser.yml 1.1 KB
- templates/go-plugin/docker-compose.yml 431 B
- templates/go-plugin/go.mod 64 B
- templates/go-plugin/hooks/command 3.9 KB
- templates/go-plugin/main_test.go 1006 B
- templates/go-plugin/main.go 1.9 KB
- templates/go-plugin/plugin.yml 974 B
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.
- yesterday First seen · 152 lines · 120 tokens per session scan A c70718646f2c
buildkite-plugin-dev is a skill published in the GitHub repository hasithaishere/buildkite-developer-toolkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 120 tokens to every session and 2,140 once invoked, about $0.0006 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
nemoclaw-contributor-implement-issue
Implement an accepted NemoClaw GitHub issue in the current checkout. Use when a user asks to pick up an issue for implementation, implement or fix a named issue, or add the issue's tests. Confirm accepted scope, deliver the smallest independently valuable capability slice, and record validation and remaining gates…
amazon-bestseller-listing
Amazon Best Sellers listing scraper: extract product cards from any Amazon Best Sellers (zgbs) or /gp/bestsellers/ category page — returns rank (position on chart), asin, title, url, image, imageAlt, price, stars, reviewCount, ratingRaw per item, plus category metadata (categoryName, categoryFullName, categoryUrl) and…
amazon-reviews-api-skill
This skill helps users automatically extract Amazon product reviews via the Amazon Reviews API. Agent should proactively apply this skill when users express needs like getting reviews for Amazon product with ASIN B07TS6R1SF, analyzing customer feedback for a specific Amazon item, getting ratings and comments for a…
amazon-competitor-analyzer
Scrapes Amazon product data from ASINs using browseract.com automation API and performs surgical competitive analysis. Compares specifications, pricing, review quality, and visual strategies to identify competitor moats and vulnerabilities.
cabloy-worktree-environment
This skill must be used only when the user explicitly invokes /cabloy-worktree-environment or explicitly asks to perform the named Cabloy worktree-environment setup. It prepares a confirmation-gated, worktree-local Vona and Zova runtime environment for a linked Cabloy Basic or Cabloy Start Git worktree using Git…
shopify-hydrogen
Hydrogen storefront implementation cookbooks. Some of the available recipes are: B2B Commerce, Bundles, Combined Listings, Custom Cart Method, Dynamic Content with Metaobjects, Express Server, Google Tag Manager Integration, Infinite Scroll, Legacy Customer Account Flow, Markets, Partytown + Google Tag Manager…