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/mixedbread-ai/mgrep/refactorgit clone --depth 1 https://github.com/mixedbread-ai/mgrepWhat 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 | $0.00000 | $0.00280 |
| Opus 5 | $0.00000 | $0.00140 |
| Sonnet 5 | $0.00000 | $0.00056 |
| Haiku 4.5 | $0.00000 | $0.00028 |
Grade A, and why
refactor 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.
What it actually says
Refactor
Safely refactor code while maintaining functionality.
Arguments
$ARGUMENTS- Description of what to refactor and why
Steps
-
Ensure test coverage
- Run existing tests:
pnpm test - If coverage is insufficient, add tests first before refactoring
- Run existing tests:
-
Plan the refactoring
- Identify all files that will be affected
- List the changes needed in each file
- Consider breaking large refactors into smaller commits
-
Make incremental changes
- Change one thing at a time
- After each change, run:
pnpm typecheck - Commit working states frequently
-
Maintain backward compatibility (if public API)
- Keep function signatures the same where possible
- If signatures must change, update all call sites
-
Verify after completion
- Run full test suite:
pnpm test - Run type check:
pnpm typecheck - Run lint:
pnpm lint
- Run full test suite:
-
Clean up
- Remove any dead code
- Update imports if file paths changed
- Update documentation if needed
-
Commit with proper message
- Use format:
refactor(scope): description - Keep refactoring commits separate from feature/fix commits
- Use format:
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 · 42 lines · 0 tokens per session scan A db99d546914a
refactor is a command published in the GitHub repository mixedbread-ai/mgrep (4,388 stars, last pushed 4mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 280 tokens. 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.