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/mindroom-ai/mindroom/commitgit clone --depth 1 https://github.com/mindroom-ai/mindroomWhat 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 | $0.00559 |
| Opus 5 | $0.00003 | $0.00280 |
| Sonnet 5 | $0.00001 | $0.00112 |
| Haiku 4.5 | $0.00001 | $0.00056 |
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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Safe Git Commit Practices
Current Status
- Git status: !
git status - Staged changes: !
git diff --staged - Unstaged changes: !
git diff
CRITICAL Reminders
-
Selective Staging
- NEVER use
git add .orgit add -A - Add files individually:
git add <filename>or usegit commit -a - Review with
git statusbefore staging
- NEVER use
-
Why This Matters
- Project has unstaged debugging scripts
- Temporary test files must not be committed
- Configuration files with credentials need protection
- Only commit relevant changes from current work
-
Pre-commit Validation
- ALWAYS run:
pre-commit run --all-files - Ensures code style compliance
- Fixes linting issues automatically
- Validates Python formatting with ruff
- ALWAYS run:
-
Commit Message Style Guide
- Format:
type(scope): description(conventional commits) - Types: feat, fix, docs, style, refactor, test, chore, perf, ci, build, revert
- Scope: Include in parentheses when clear module/area affected
- Description rules:
- Use lowercase after colon (unless proper nouns: Docker, Matrix, AI)
- Keep first line under 72 characters
- Use imperative mood ("Add" not "Added", "Fix" not "Fixed")
- Be specific about what changed
- For bugs: describe what was broken
- For features: describe capability added
- For refactors: explain what was restructured
Good examples:
feat: Add Direct Message (DM) support for private agent conversationsfix(profile): Handle null user data in profile loadingrefactor: Extract team formation logic into private functiontest: Add comprehensive tests for extra_kwargs functionalitydocs: Add comprehensive deployment guide for instance manager
For incomplete work:
WIP: [description]is acceptable - Format:
-
Final Checks
- Run
pytestto ensure tests pass - Review
git diff --staged - Verify no unrelated files included
- Check for sensitive information
- Run
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 · 61 lines · 7 tokens per session scan A 0718cd897795
commit is a command published in the GitHub repository mindroom-ai/mindroom (254 stars, last pushed 2d ago), licensed Apache-2.0. It adds 7 tokens to every session and 559 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.