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/sterlingchin/marvin-template/commitgit clone --depth 1 https://github.com/SterlingChin/marvin-templateWhat 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 | $0.00007 | $0.00626 |
| Opus 5 | $0.00003 | $0.00313 |
| Sonnet 5 | $0.00001 | $0.00125 |
| Haiku 4.5 | $0.00001 | $0.00063 |
Grade A, and why
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 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.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/commit - Git Commit Workflow
Review uncommitted changes and create logical, well-organized commits.
Instructions
1. Check Current State
Run git status and git diff --stat to see all changes.
2. Group Changes
Identify logical groupings. Don't over-split: 2-4 commits is usually right, and one commit is fine if the changes are related.
| Group | Files | Commit Type |
|---|---|---|
| Features/Scripts | src/*.py, *.js, new integrations |
feat: |
| Bug fixes | Any fix to existing behavior | fix: |
| Refactoring | Restructured code, no behavior change | refactor: |
| Commands/Agents/Skills | .claude/commands/, .claude/agents/, .claude/skills/ |
feat: or chore: |
| Config | CLAUDE.md, config.yaml, *.json |
chore: |
| Content | content/, research/ |
content: |
| Documentation | *.md (non-state, non-session) |
docs: |
| State/Sessions | state/, sessions/ |
chore: |
3. Commit Order
Follow this ordering discipline:
- Dependencies first - If commit B uses something from commit A, commit A goes first
- Features before docs - Ship the feature, then document it
- Content before state - Content is the work, state is the record of it
- State/sessions always last - These are metadata about the session
4. Create Commits
For each logical group:
git add <relevant-files>
git commit -m "$(cat <<'EOF'
<type>: <short description>
<optional body: explain WHY, not what. One sentence is enough.>
Co-Authored-By: Claude <[email protected]>
EOF
)"
The subject line should be a concise summary. Use the optional body when the "why" isn't obvious from the subject.
5. Push (if requested)
After all commits are created:
git push
6. Verify
Show the commits created:
git log --oneline -5
Commit Types
| Type | Use For |
|---|---|
feat |
New features, scripts, commands, agents, integrations |
fix |
Bug fixes |
refactor |
Code restructuring with no behavior change |
docs |
Documentation, setup guides |
content |
Blog posts, research, content files |
chore |
Config, maintenance, state updates, session logs |
perf |
Performance improvements |
ci |
CI/CD pipeline changes |
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 · 76 lines · 7 tokens per session scan A 080940b83d28
commit is a command published in the GitHub repository SterlingChin/marvin-template (1,014 stars, last pushed 14d ago), licensed MIT. It adds 7 tokens to every session and 626 once invoked, about $0.0000 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.