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/christopher-buss/bedrock/refactorgit clone --depth 1 https://github.com/christopher-buss/bedrockWhat 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 | $0.00014 | $0.01009 |
| Opus 5 | $0.00007 | $0.00504 |
| Sonnet 5 | $0.00003 | $0.00202 |
| Haiku 4.5 | $0.00001 | $0.00101 |
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 today.
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
83% identical to cycle — 136 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.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply this document (specifically the Refactor phase), to the info given by user input here: $ARGUMENTS
(If there was no info above, fallback to the context of the conversation)
TDD Fundamentals
The TDD Cycle
The foundation of TDD is the Red-Green-Refactor cycle:
-
Red Phase: Write ONE failing test that describes desired behavior
- The test must fail for the RIGHT reason (not syntax/import errors)
- Only one test at a time - this is critical for TDD discipline
- Exception: For browser-level tests or expensive setup (e.g., Storybook
*.stories.tsx), group multiple assertions within a single test block to avoid redundant setup - but only when adding assertions to an existing interaction flow. If new user interactions are required, still create a new test. Split files by category if they exceed ~1000 lines.
- Exception: For browser-level tests or expensive setup (e.g., Storybook
- Adding a single test to a test file is ALWAYS allowed - no prior test output needed
- Starting TDD for a new feature is always valid, even if test output shows unrelated work
- Avoid hard-coded timeouts both in form of sleep() or timeout: 5000 etc;
use proper async patterns (
waitFor,findBy*, event-based sync) instead and rely on global test configs for timeout settings
-
Green Phase: Write MINIMAL code to make the test pass
- Implement only what's needed for the current failing test
- No anticipatory coding or extra features
- Address the specific failure message
-
Refactor Phase: Improve code structure while keeping tests green
- Only allowed when relevant tests are passing
- Requires proof that tests have been run and are green
- Applies to BOTH implementation and test code
- No refactoring with failing tests - fix them first
Core Violations
- Multiple Test Addition
- Adding more than one new test at once
- Exception: Initial test file setup or extracting shared test utilities
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.
- today First seen · 105 lines · 14 tokens per session scan A 4c11064225e7
refactor is a command published in the GitHub repository christopher-buss/bedrock (13 stars, last pushed yesterday), licensed MIT. It adds 14 tokens to every session and 1,009 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 83% identical to cycle, differing in 136 lines, and is treated as a copy.
Other commands, from other repositories
sicario.verify
Run deterministic verification.
create-plan
Important: ALL phases must use checkmarks for their tasks. Each checkmark should correspond to a single commit. The checkmark should be marked - [x] in the same commit that completes the task. Phase tasks should be prefixed with parent phase number and letters (a, b, c, etc.).
sicario.controls
Generate or update docs/compliance/control-applicability.md.
sicario.assess
Assess the repository against SicarioSpec guardrails.
sicario.review
Review the active spec, plan, tasks, staged changes, or branch for security and governance gaps.
sicario.threatmodel
Create or update docs/security/threat-model.md from the active spec and plan.