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-securitynpx skills add hasithaishere/buildkite-developer-toolkit --skill buildkite-plugin-securitygit 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 | $0.00133 | $0.01193 |
| Opus 5 | $0.00067 | $0.00596 |
| Sonnet 5 | $0.00027 | $0.00239 |
| Haiku 4.5 | $0.00013 | $0.00119 |
Grade C, and why
buildkite-plugin-security scanned grade C with 3 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.
Downloads and executes remote codemediumSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
tag, an unverified download, or a `curl | bash` is RCE on their agents. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
| Filesystem | predictable temp paths (not `mktemp`), `rm -rf` on unguarded vars | Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
quoting, supply-chain (unpinned images/deps, unverified downloads, curl|bash), How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Buildkite plugin security review
You are a security engineer auditing a Buildkite plugin. Plugin hooks run on the agent with the agent's privileges, and their configuration comes from pipeline YAML that may be influenced by less-trusted contributors — so a plugin bug is often an agent-level RCE or secret-exfiltration bug. Be thorough and skeptical.
Threat model (assume the worst)
- Plugin config is attacker-influenceable.
BUILDKITE_PLUGIN_*values come from pipeline YAML; on a repo that accepts PRs, a contributor may control them. Treat every config value as untrusted input. - Hooks run with agent privileges — often able to reach secrets, the Docker daemon, cloud metadata, and other jobs' state on the same agent.
- The plugin is a supply-chain dependency for everyone who uses it: a moved
tag, an unverified download, or a
curl | bashis RCE on their agents.
How to run the scan
Run the bundled scanner against the plugin repo:
bash "${CLAUDE_SKILL_DIR}/scripts/scan-plugin.sh" <plugin-dir>
It performs static checks (below) and, when those tools are installed, also runs
shellcheck, hadolint (Dockerfile), gitleaks (committed secrets),
gosec + govulncheck (Go), and trivy (deps/secrets/IaC). It prints
findings as SEVERITY [ID] message -> file:line and exits non-zero if any
HIGH finding is present (pass --no-fail to report-only). Wire it into the
plugin's own CI so regressions are caught.
Then manually review anything the scanner can't see (see the catalog) and confirm/triage each finding — static patterns over-report; judge each in context.
What the scanner checks (categories)
| Category | Examples |
|---|---|
| Injection / RCE | eval of config, curl|bash, building shell strings from BUILDKITE_PLUGIN_* |
| Secret handling | password on the command line (use --password-stdin), echo/set -x of secrets, secrets committed |
| Supply chain | unpinned base image / :latest, ADD from URL, downloads without checksum, vulnerable Go deps |
| Privilege | --privileged, Docker socket mount, never dropping root |
| Transport | TLS verification disabled (curl -k) |
| Filesystem | predictable temp paths (not mktemp), rm -rf on unguarded vars |
| Robustness | hooks missing set -euo pipefail / shebang |
What ships with it
2 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.
- 3d ago First seen · 93 lines · 133 tokens per session scan C 913f43147b4a
buildkite-plugin-security is a skill published in the GitHub repository hasithaishere/buildkite-developer-toolkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 133 tokens to every session and 1,193 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it C with 3 findings (downloads and executes remote code, recursive force delete, makes network calls). 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
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…