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 commands/d-padmanabhan/agent-engineering-handbook/ghagit clone --depth 1 https://github.com/d-padmanabhan/agent-engineering-handbookWrote 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/commands/d-padmanabhan/agent-engineering-handbook/gha)<a href="https://agentmods.dev/commands/d-padmanabhan/agent-engineering-handbook/gha"><img src="https://agentmods.dev/badge/commands/d-padmanabhan/agent-engineering-handbook/gha.svg" alt="Measured on agentmods" 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 | $0.00017 | $0.00477 |
| Opus 5 | $0.00009 | $0.00238 |
| Sonnet 5 | $0.00003 | $0.00095 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
gha 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 6d 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.
What it actually says
GITHUB ACTIONS MODE ACTIVATED
You are now in GITHUB ACTIONS MODE. Any work on GitHub Actions MUST follow:
rules/160-github-actions.mdc(secure, least-privilege workflows)rules/100-core.mdc(minimal, maintainable changes)rules/310-security.mdc(no secrets, supply-chain aware)
Use this command when the user asks to:
- Create a new workflow under
.github/workflows/ - Modify an existing workflow
- Review a workflow for security/correctness
Guardrails (mandatory)
- Least privilege: prefer job-level
permissions:with minimal scopes. - No secrets in code: never paste tokens/keys; reference
${{ secrets.* }}only. - Pin actions safely: use stable major tags (e.g.,
actions/checkout@v4) unless policy requires SHA pinning. - Avoid remote writes unless explicitly requested (PR creation/merge, releases, etc.).
Step 0: Determine intent (create vs modify vs review)
Infer intent from the user’s request. If ambiguous, ask ≤3 clarifying questions (trigger events, required permissions, target runners, required secrets/vars).
Create
Produce a complete workflow that is:
- Minimal and readable
- Uses least-privilege permissions
- Uses caches only when justified
- Has clear job names, step names, and failure modes
Modify
- Keep changes localized to the requested behavior
- Preserve existing triggers and permissions unless the user asked to change them
- Prefer tightening permissions over broadening
Review
Prioritize:
- Critical: overbroad permissions, untrusted
pull_request_targetmisuse, secrets exposure, unsafe checkout of PR code with secrets, running arbitrary scripts from forks - Recommended: caching correctness, pinned tool versions, concurrency controls
- Optional: readability and naming
Verification (as applicable):
pre-commit run --all-files
Done condition
End with:
- Files changed (or “no changes made”)
- How to validate (lint/checks) and expected workflow behavior
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.
- 6d ago First seen · 65 lines · 17 tokens per session scan A 681997d66bc5
gha is a command published in the GitHub repository d-padmanabhan/agent-engineering-handbook (16 stars, last pushed 6d ago), licensed MIT. It adds 17 tokens to every session and 477 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 commands, from other repositories
monitor-ci
You are the orchestrator for monitoring Nx Cloud CI pipeline executions and handling self-healing fixes. You spawn the ci-monitor-subagent subagent to poll CI status and make decisions based on the results.
dart-fix-ci
Command "dart-fix-ci" from dartsim/dart, covering required reading, workflow and output.
domains
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
access
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
check-release-health
Summarize the CI health of an OpenShift release using live data from the openshift-ci-mcp server.
analyst
Use when performing local analyst review before pushing PR changes. Assesses code quality, impact analysis, and maintainability.