Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/KalarisLabs/Skill-Doctornpx agentmods add skills/kalarislabs/skill-doctor/ci-cdWrote 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/kalarislabs/skill-doctor/ci-cd)<a href="https://agentmods.dev/skills/kalarislabs/skill-doctor/ci-cd"><img src="https://agentmods.dev/badge/skills/kalarislabs/skill-doctor/ci-cd/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/kalarislabs/skill-doctor/ci-cd"><img src="https://agentmods.dev/badge/skills/kalarislabs/skill-doctor/ci-cd.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 | $0.00046 | $0.00636 |
| Opus 5 | $0.00023 | $0.00318 |
| Sonnet 5 | $0.00009 | $0.00127 |
| Haiku 4.5 | $0.00005 | $0.00064 |
Grade A, and why
ci-cd 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 today.
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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CI/CD
Canonical policy: TESTING.md. Workflows must match it. If you change a required check, update TESTING.md in the same PR.
Every commit / every PR (required, must stay fast)
Job names (branch protection should match these strings):
lint-and-unit— fmt, clippy-D warnings,cargo test --workspace --locked, invariant grepos-cli (ubuntu-latest)/(macos-latest)/(windows-latest)— build CLI,--help,version, later: benign exit 0 and SD-02 exit 2supply-chain—cargo deny, gitleaks
Keep this path under ~8 minutes on cache hit. Use Swatinem/rust-cache. OS matrix fail-fast: false.
Do not put on this path: TestMu Kane, competitor benches, musl cross, cargo publish, npm publish, coverage fail gates during bootstrap.
Not every commit
| Workflow | Trigger | Why |
|---|---|---|
testmu.yml |
label e2e, nightly, main, workflow_dispatch |
Kane/LambdaTest is slow, billed, AI-flaky |
bench.yml |
nightly + tags | Docker competitor pulls |
release.yml |
tags v* only |
musl, SBOM, Sigstore, crates.io, npm |
How an agent should add CI
- New product behavior → add a unit/CLI test first. CI already runs
cargo test. - New tooling (deny, gitleaks, a matrix OS) → add a job in
ci.ymlonly if it belongs on every commit. - New expensive check → new workflow, non-required, document in
TESTING.md. - Never store tokens in YAML. Use existing secrets:
NPM_TOKEN,CARGO_REGISTRY_TOKEN,LT_USERNAME,LT_ACCESS_KEY. - Pin action versions; prefer SHA once v2 is tagged.
- Do not add a fourth review bot. CodeRabbit / Greptile / Intelligence AI are PR comments, not required checks.
Local commands agents must run before claiming CI will pass
cargo fmt --all --check
cargo clippy --workspace --all-targets -- -D warnings
cargo test --workspace --locked
./scripts/prepublish-check.sh --fast
--full is the pre-tag gate (deny + publish dry-run). Never cargo publish / npm publish from a feature branch.
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.
- today First seen · 53 lines · 46 tokens per session scan A 774d17045be6
ci-cd is a skill published in the GitHub repository KalarisLabs/Skill-Doctor (11 stars, last pushed today), licensed Apache-2.0. It adds 46 tokens to every session and 636 once invoked, about $0.0002 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 2026-09-11.
Other skills, from other repositories
terraform-skill
Terraform infrastructure as code best practices.
continuous-llm-red-teaming-with-promptfoo
Wire Promptfoo and DeepTeam into CI/CD for automated regression red-teaming of LLM apps against OWASP LLM Top 10 and OWASP Agentic presets, failing the build when jailbreak or injection vulnerabilities regress.
panguard
AI agent security platform — audit skills, scan for threats, and run 24/7 protection with 9,700+ detection rules.
clawmoat
Real-time AI agent security scanner. Detects prompt injection, jailbreak attempts, credential/secret leaks, PII exposure, and dangerous tool calls. Activate when: (1) scanning inbound messages or tool outputs for prompt injection, (2) checking outbound content for credential leaks or PII, (3) auditing agent session…
prompt-injection-auditor
Security audit of LLM system prompts, agent instruction files (SKILL.md, AGENTS.md, CLAUDE.md), and agent configurations against prompt injection attacks. Use when the user wants to (1) audit or harden a system prompt or agent instructions against prompt injection, (2) review an agent skill or system prompt for…
usap-devsecops
DevSecOps pipeline security engineer (cs-devsecops-engineer). Use for pipeline security reviews, SAST/DAST result analysis, PR security gates, CI/CD hardening, supply chain risk, SBOM generation, or when the user says "pipeline security", "scan this PR", "CI/CD security", or "DevSecOps".