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/pythongit clone --depth 1 https://github.com/d-padmanabhan/agent-engineering-handbookWhat 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 | $0.00013 | $0.00384 |
| Opus 5 | $0.00006 | $0.00192 |
| Sonnet 5 | $0.00003 | $0.00077 |
| Haiku 4.5 | $0.00001 | $0.00038 |
Grade A, and why
python 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 2d 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
PYTHON MODE ACTIVATED
You are now in PYTHON MODE. Any work on Python code MUST follow:
rules/200-python.mdc(opinionated Python guidance)rules/100-core.mdc(minimal, production-ready changes)rules/310-security.mdc(no secrets, OWASP-minded)
Use this command when the user asks to:
- Create new Python modules/functions/classes
- Modify existing Python code
- Review Python code for correctness/security/performance
Guardrails (mandatory)
- Prefer stdlib over new dependencies unless explicitly justified.
- Validate inputs and fail fast with clear errors.
- Don’t log secrets (mask sensitive fields).
- Keep changes minimal; don’t refactor unrelated code.
Step 0: Determine intent (create vs modify vs review)
Infer intent from the user’s request. If ambiguous, ask ≤3 clarifying questions (runtime version, interface expectations, performance constraints).
Create
Produce complete, runnable code with:
- Type hints
- Clear docstrings where appropriate
- Error handling for expected failures
Modify
- Preserve existing behavior unless requested otherwise
- Prefer minimal diffs
- Add tests only if requested (or if needed to prevent regression)
Review
Prioritize:
- Critical: injection risks, insecure subprocess usage, secret leakage, broken authz, unsafe deserialization
- Recommended: performance hot spots, poor error handling, observability gaps
- Optional: style and small readability tweaks
Verification (as applicable):
pre-commit run --all-files
Done condition
End with:
- Files changed (or “no changes made”)
- How to validate (tests/lint/type-check) and expected 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.
- 2d ago First seen · 64 lines · 13 tokens per session scan A 2610a43ad5ee
python is a command published in the GitHub repository d-padmanabhan/agent-engineering-handbook (15 stars, last pushed 2d ago), licensed MIT. It adds 13 tokens to every session and 384 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.