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.
git clone --depth 1 https://github.com/stefan-jansen/claude-code-toolkitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/stefan-jansen/claude-code-toolkit/fix)<a href="https://agentmods.dev/commands/stefan-jansen/claude-code-toolkit/fix"><img src="https://agentmods.dev/badge/commands/stefan-jansen/claude-code-toolkit/fix/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/stefan-jansen/claude-code-toolkit/fix"><img src="https://agentmods.dev/badge/commands/stefan-jansen/claude-code-toolkit/fix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00009 | $0.00533 |
| Opus 5.5 | $0.00004 | $0.00213 |
| Sonnet 5.5 | $0.00002 | $0.00107 |
| Haiku 4.5 | $0.00001 | $0.00053 |
Grade A, and why
fix 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 1mo 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
Universal Fix & Debug
Input: $ARGUMENTS
Usage
# Debug Mode
/fix "TypeError: 'NoneType' has no attribute 'get'"
/fix src/auth.py
/fix "Failed tests in test_user.py"
# Apply Fixes Mode
/fix review # Apply fixes from recent review
/fix audit # Apply fixes from audit results
/fix all # Apply all available fixes
Process
1. Determine Mode
- Debug: Error messages, stack traces, file references → investigate and fix
- Apply: "review", "audit", "all" → apply structured fixes from analysis files
2. Debug Mode
- Parse error message/stack trace
- Locate source files and lines
- Gather context (dependencies, related code)
- Identify root cause
- Verify APIs with Serena before writing fix
- Apply minimal targeted fix
- Test and verify resolution
3. Apply Fixes Mode
- Load fix recommendations from review/audit files
- Categorize: code quality, bugs, performance, security
- Apply fixes systematically (critical first)
- Validate each change
- Document results
4. Verification
- Run relevant tests
- Check linting
- Verify functionality preserved
- Update documentation if needed
Serena Enhancement
When available (70-90% token reduction):
find_symbol→ locate exact functions/classes in errorsfind_referencing_symbols→ understand usage patternsget_symbols_overview→ module structure without reading filesreplace_symbol_body→ surgical fixes to specific methods
Example workflow:
# Error: "AttributeError: 'User' object has no attribute 'email'"
find_symbol User # Find class definition
find_referencing_symbols User # Check usage
replace_symbol_body User/get_email # Apply targeted fix
Fallback: File reading + grep-based analysis
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.
- 1mo ago First seen · 70 lines · 9 tokens per session scan A dc2ff009dbd9
fix is a command published in the GitHub repository stefan-jansen/claude-code-toolkit (90 stars, last pushed 3mo ago), licensed MIT. It adds 9 tokens to every session and 533 once invoked, about $0.0000 per session on Opus 5.5. 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
verify-loop
A command that repeatedly checks recent code changes and tries to fix failures, with a configurable retry limit. It can run code review, builds, tests, linting, and type checks according to the project language.
build-fix
A build-error fixing procedure for TypeScript projects. It runs the project build, groups and explains errors, applies fixes one at a time, and checks the build again.
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524) — sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.
investigate
Systematic root-cause debugging — find the cause before writing any fix.
gates-csk
Gate report — what the tool-level gates actually did, and which rules nothing has tripped.
optimize
Analyze and suggest performance improvements for code, queries, or systems.