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/zevtos/agentpipe/refactorgit clone --depth 1 https://github.com/zevtos/agentpipeWhat 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 | $0.00027 | $0.00784 |
| Opus 5 | $0.00014 | $0.00392 |
| Sonnet 5 | $0.00005 | $0.00157 |
| Haiku 4.5 | $0.00003 | $0.00078 |
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.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are orchestrating a safe refactoring. The #1 rule: refactoring must not change external behavior. Every step must preserve the existing test suite passing.
Context
@CLAUDE.md
Refactoring Goal
$ARGUMENTS
Pipeline
Step 1: Detect — MANDATORY
You MUST use the Agent tool with subagent_type: "refactorer" to run the refactorer agent. Do NOT skip this step.
Prompt for the refactorer agent: "Analyze this codebase for refactoring opportunities. Focus area: $ARGUMENTS
Scan for:
- Code duplication and clone groups
- Code smells (god functions, feature envy, primitive obsession, unnecessary complexity)
- Dead code and unreachable branches
- Single source of truth violations (constants/config defined in multiple places)
- Test suite problems (meaningless tests, duplicate patterns, missing factories)
- Scalability issues (adding a new type requires changes in 5+ files)
Produce a prioritized findings report with specific file:line locations and fixes."
Wait for the refactorer agent to complete. Present its findings to the user.
Ask: "Found [count] findings ([high/medium/low breakdown]). This is a [RISK] refactor. Proceed with fixes?"
Step 2: Safety Net (Tester Agent — if needed)
If test coverage is insufficient for the refactored code, run the tester agent:
"Write characterization tests for the following code BEFORE refactoring:
[list files/functions being refactored from refactorer findings]
These tests must capture the CURRENT behavior exactly — they serve as a safety net.
Focus on: all public API surfaces, edge cases, error paths."
Run the characterization tests to verify they pass.
Step 3: Architecture Review (Architect Agent — if structural)
If the refactorer found structural issues (module boundaries, API contracts, decomposition), run the architect agent:
"Review this refactoring plan:
Goal: $ARGUMENTS
Refactorer findings: [paste structural findings]
Evaluate:
- Is this the right decomposition?
- Are the new boundaries clean?
- Does this create better or worse coupling?
- Any migration concerns?"
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 · 87 lines · 27 tokens per session scan A 4948322bffa8
refactor is a command published in the GitHub repository zevtos/agentpipe (11 stars, last pushed 2mo ago), licensed MIT. It adds 27 tokens to every session and 784 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 2026-08-30.
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.