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/zgsm-ai/costrict/commitgit clone --depth 1 https://github.com/zgsm-ai/costrictWhat 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 | $0.00008 | $0.00629 |
| Opus 5 | $0.00004 | $0.00315 |
| Sonnet 5 | $0.00002 | $0.00126 |
| 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 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.
This is a copy
100% identical to commit — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
-
Analyze the current changes to understand what needs to be committed:
# Check for staged and unstaged changes git status --short # View the diff of all changes (staged and unstaged) git diff HEAD -
Based on the diff output, formulate a commit message following conventional commit format:
- feat: New feature or functionality
- fix: Bug fix
- refactor: Code restructuring without behavior change
- docs: Documentation changes
- test: Adding or updating tests
- chore: Maintenance tasks, dependencies, configs
- style: Formatting, whitespace, no logic changes
Format:
type(scope): brief descriptionExamples:
feat(api): add user authentication endpointfix(ui): resolve button alignment on mobilerefactor(core): simplify error handling logicdocs(readme): update installation instructions
-
Stage all unstaged changes:
git add -A -
Commit with the generated message:
git commit -m "type(scope): brief description"If pre-commit hooks fail:
- Review the error output (linter errors, type checking errors, etc.)
- Fix the identified issues in the affected files
- Re-stage the fixes:
git add -A - Retry the commit:
git commit -m "type(scope): brief description"
-
Push to the remote repository:
git pushIf pre-push hooks fail:
- Review the error output (test failures, linter errors, etc.)
- Fix the identified issues in the affected files
- Stage and commit the fixes using steps 3-4
- Retry the push:
git push
Tips for good commit messages:
- Keep the first line under 72 characters
- Use imperative mood ("add", "fix", "update", not "added", "fixes", "updated")
- Be specific but concise
- If multiple unrelated changes exist, consider splitting into separate commits
Common hook failures and fixes:
- Linter errors: Run the project's linter (e.g.,
npm run lintorpnpm lint) to see all issues, then fix them - Type checking errors: Run type checker (e.g.,
npx tsc --noEmit) to identify type issues - Test failures: Run tests (e.g.,
npm testorpnpm test) to identify failing tests and fix them - Format issues: Run formatter (e.g.,
npm run formatorpnpm format) to auto-fix formatting
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 · 77 lines · 8 tokens per session scan A bb9e4cb8a10e
commit is a command published in the GitHub repository zgsm-ai/costrict (4,397 stars, last pushed 13d ago), licensed Apache-2.0. It adds 8 tokens to every session and 629 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to commit, differing in 4 lines, and is treated as a copy.
Other commands, from other repositories
bump-plugin
Bump changed plugin and marketplace version.
commit-push-pr
Run tests, commit current work, push, and open a PR.
release
Release specship to npm via publish.sh (dry-run first).
analyst-init
Before executing this command, CONFIRM these files exist and are readable.
architect-finalize-arch
Before executing this command, CONFIRM these files exist and are readable.
codebase-detection
Before executing this command, CONFIRM these files exist and are readable.