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/code-commitgit 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 | $0.00022 | $0.01266 |
| Opus 5 | $0.00011 | $0.00633 |
| Sonnet 5 | $0.00004 | $0.00253 |
| Haiku 4.5 | $0.00002 | $0.00127 |
Grade A, and why
code-commit 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CODE COMMIT MODE ACTIVATED
You are running the /code-commit workflow to prepare a clean commit and push it to origin.
[!IMPORTANT] This workflow includes remote writes (
git push) and is HITL gated. Do not commit or push until the user explicitly approves.
Step 0: Repo safety and context
If you are not sure which repo you are in, STOP and ask the user to confirm.
Collect context:
- Repo root:
git rev-parse --show-toplevel - Current branch:
git branch --show-current - Current HEAD:
git rev-parse HEAD - Remote:
git remote -v
Step 1: Review all changes
Review working tree and index:
git statusgit diffgit diff --cached
List changed files explicitly (for safe staging later):
git status --porcelain=v1- Derive the exact file list from porcelain output (do not guess)
Step 2: Format and clean up (language-aware)
Detect the project language/framework based on modified files and run the appropriate formatter/linter. If a tool is not installed or a project file is missing, report the reason and continue with the closest substitute.
Bash
shfmt -w -i 2 -ci -sr -bn <changed_shell_files>shellcheck <changed_shell_files>
GitHub Actions
If workflows exist, run:
actionlint .github/workflows/*.yaml .github/workflows/*.yml
Terraform
terraform fmt -recursiveterraform validatetflint
Python
Run (as applicable in this repo):
isort <changed_python_files>ty <changed_python_files>(ormypy <changed_python_files>)pylint <changed_python_files>(aim for ≥ 9.5)ruff format <changed_python_files>ruff check <changed_python_files> --fixblack <changed_python_files>(if used in repo)tox(if applicable / configured)
[!NOTE] If you change behavior while fixing docstrings, call it out in the summary.
Go
gofmt -w -s <changed_go_files>go vet ./...staticcheck ./...golangci-lint run ./...govulncheck ./...
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 · 199 lines · 22 tokens per session scan A a99faa4de032
code-commit is a command published in the GitHub repository d-padmanabhan/agent-engineering-handbook (15 stars, last pushed 2d ago), licensed MIT. It adds 22 tokens to every session and 1,266 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.