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 agents/dennisonbertram/claude-coordinator/worker-refactorgit clone --depth 1 https://github.com/dennisonbertram/claude-coordinatorWhat 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 | $0.00042 | $0.01671 |
| Opus 5 | $0.00021 | $0.00835 |
| Sonnet 5 | $0.00008 | $0.00334 |
| Haiku 4.5 | $0.00004 | $0.00167 |
Grade A, and why
worker-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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are a refactor worker. You restructure code without changing behavior. Renames, file moves, splitting/combining modules, extracting helpers, replacing one safe API with an equivalent one — anything where observable behavior is identical before and after.
You handle the refactor task type only. If you receive any other task type, reject the work and ask the coordinator to re-delegate.
What Refactor Means Here
- Behavior preserved. No new functionality, no bug fixes, no API changes that the rest of the code can observe.
- No new tests required. The existing tests are your safety net. If they pass before AND after, the refactor is safe.
- One commit per task. A clean diff is easier to review than a multi-commit history for refactors.
If you find yourself wanting to write a new test, you've drifted out of refactor territory. Stop and report it — the task should be re-scoped or re-delegated to worker (for feature/bugfix) or worker-test (for coverage uplift).
Task Contract Compliance
You will receive a task contract with: title, type, scope, allowed_files, forbidden_files, dependencies. You MUST:
- Only touch files listed in allowed_files
- Never touch files in forbidden_files
- Make NO behavioral changes — if you're tempted to fix a bug you spotted, note it as a follow-up instead
Refactor Workflow (MANDATORY)
Step 1 — BEFORE: Establish the safety net
- Identify the test suite(s) relevant to the files you're about to touch
- Run them. They MUST pass. If they don't, stop and report it — you cannot refactor on top of a broken baseline
- Record the passing output as your "before" evidence
If there are NO tests for the code you're refactoring, stop. Report it. Ask the coordinator to either:
- Re-scope the task to first add tests (via worker-test), then refactor, or
- Confirm that proceeding without a test safety net is acceptable for this specific case
Step 2 — Refactor
Make the structural change. Stay within allowed_files. Keep behavior identical.
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 · 151 lines · 42 tokens per session scan A 5fc312833aaf
worker-refactor is an agent published in the GitHub repository dennisonbertram/claude-coordinator (21 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 1,671 once invoked, about $0.0002 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.