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/jnarowski/agentcmd/commit-and-pushgit clone --depth 1 https://github.com/jnarowski/agentcmdWhat 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 | $0.00011 | $0.01006 |
| Opus 5 | $0.00005 | $0.00503 |
| Sonnet 5 | $0.00002 | $0.00201 |
| Haiku 4.5 | $0.00001 | $0.00101 |
Grade A, and why
commit-and-push 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit and Push
Analyze changes, create a commit with auto-generated message following team conventions, push to remote, and create a pull request if one doesn't exist. Fails gracefully if there are no changes to commit.
Variables
- $base-branch: $1 (optional) - The base branch for the PR (defaults to
main)
Instructions
- NEVER run additional commands to read or explore code beyond git commands
- NEVER use the TodoWrite or Task tools
- Follow the exact git commit conventions from the codebase (include Claude footer)
- If there are no changes (no untracked files, no modifications), stop gracefully and inform the user
- NEVER skip git hooks or use --no-verify
- If commit fails due to pre-commit hook, report the error and stop - do not retry
- Use HEREDOC for commit messages to ensure proper formatting
- Always check if PR already exists before creating a new one
- Default to
mainas base branch if $base-branch is not provided
Workflow
-
Check for changes and analyze
- Run these commands in parallel:
git status,git diff, andgit log -3 --oneline git status: See all untracked files and modificationsgit diff: See staged and unstaged changesgit log -3 --oneline: Understand commit message style- If no changes exist, stop and inform user - DO NOT proceed
- Run these commands in parallel:
-
Create commit
- Draft a concise commit message (1-2 sentences) based on the changes
- Summarize the nature of changes (new feature, enhancement, bug fix, refactoring, test, docs, etc.)
- Add all relevant changes:
git add -A - Create commit with message ending with:
🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <[email protected]> - Use HEREDOC format:
git commit -m "$(cat <<'EOF' Your commit message here. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <[email protected]> EOF )" - Run
git statusafter commit to verify success
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 · 108 lines · 11 tokens per session scan A 9b7986c9d485
commit-and-push is a command published in the GitHub repository jnarowski/agentcmd (18 stars, last pushed 8mo ago), licensed MIT. It adds 11 tokens to every session and 1,006 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 2026-09-01.
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.