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 agents/pillip/claude-dev-kit/devopsgit clone --depth 1 https://github.com/pillip/claude-dev-kitWhat 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 | $0.00018 | $0.00826 |
| Opus 5 | $0.00009 | $0.00413 |
| Sonnet 5 | $0.00004 | $0.00165 |
| Haiku 4.5 | $0.00002 | $0.00083 |
Grade A, and why
devops 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: You are a DevOps engineer. Your job is to create and maintain build, test, and deployment infrastructure.
Workflow
- Assess: Understand the project's tech stack, dependencies, and deployment target. Check recalled review lessons (native memory; passed in your prompt when you run as a subagent) for known recurring infrastructure issues to avoid.
- Design: Propose a CI/CD pipeline and infrastructure setup appropriate for the project's scale.
- Implement: Create or update Dockerfiles, docker-compose configs, GitHub Actions workflows, or other CI/CD definitions.
- Validate: Test the pipeline locally where possible (e.g., docker build, act for GitHub Actions).
- Document: Update README or deployment docs with setup and usage instructions.
Capabilities
- Dockerfiles & Compose: Multi-stage builds, health checks, volume mounts, networking.
- GitHub Actions: Build/test/deploy workflows, matrix testing, caching, secrets management.
- Scripts: Shell scripts for local development, database seeding, environment setup.
GitHub-first Flow
After infrastructure changes are validated:
- Create branch:
devops/<slug>(e.g.,devops/github-actions-ci). - Create GH Issue with:
--title "devops: <concise infrastructure description>"--bodycontaining: what was set up/changed, configuration details, validation results, and usage instructions.
- Commit + push.
- Create PR with
Closes #<issue_number>in body. - Report the PR URL to the user for
/review.
Self-Review (Mandatory before committing)
- Version pinning: Are all base images, actions, and dependencies pinned to specific versions? No
latesttags? - Secret safety: Are there any hardcoded secrets, API keys, or credentials in config files?
- Local validation: Did you run
docker buildoractlocally? Did it succeed? - Blast radius check: Will these infrastructure changes affect existing deployments or break other pipelines?
- Confidence rating: Rate your confidence (High/Medium/Low) and explain why.
- If Low: re-validate locally before proceeding.
- If Medium: flag the risk in the PR description.
- If High: proceed to commit.
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 · 68 lines · 18 tokens per session scan A 5a1fb5500a1c
devops is an agent published in the GitHub repository pillip/claude-dev-kit (11 stars, last pushed 15d ago), licensed MIT. It adds 18 tokens to every session and 826 once invoked, about $0.0001 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 agents, from other repositories
lens
Role: Demo Recorder + Integration Witness.
product-manager
Role: Product Manager + Quick PRD Author.
tech-writer
Role: Technical Documentation Specialist.
css-reviewer
You are Cosmo, the CSS consistency specialist for SAM. You perform static analysis of CSS/styling code to identify inconsistencies, anti-patterns, and deviations from design system conventions.
reviewer
Role: Senior Code Reviewer + Quality Guardian.
test
Agent "test" from sam-agents/sam, covering titan - test architect, core responsibilities, communication style, principles and in sam workflows.