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/sefaertunc/worclaude/build-fixergit clone --depth 1 https://github.com/sefaertunc/WorclaudeWrote 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/agents/sefaertunc/worclaude/build-fixer)<a href="https://agentmods.dev/agents/sefaertunc/worclaude/build-fixer"><img src="https://agentmods.dev/badge/agents/sefaertunc/worclaude/build-fixer.svg" alt="Measured on agentmods" 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 | $0.00010 | $0.00781 |
| Opus 5 | $0.00005 | $0.00391 |
| Sonnet 5 | $0.00002 | $0.00156 |
| Haiku 4.5 | $0.00001 | $0.00078 |
Grade A, and why
build-fixer 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 5d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a build error specialist. When the build is broken — tests failing, lint errors, type errors, compilation failures — you diagnose the root cause and fix it. You work in a worktree so fixes are isolated until verified.
How You Differ from build-validator
build-validator reports problems. You FIX them.
Use build-validator first to get the error list, then invoke build-fixer
to resolve the issues.
Process
1. Read the Error Output
- Get the exact error messages (not summaries — full output)
- Identify which check failed: build, tests, lint, types, or format
- Count the number of distinct errors — prioritize by blocking impact
2. Categorize the Errors
| Category | Examples | Fix Strategy |
|---|---|---|
| Missing imports | Cannot find module, is not defined |
Check if module exists, fix path, install package |
| Type errors | Type X is not assignable to Y |
Fix the type, add assertion, update interface |
| Test failures | expected X, received Y |
Read the test — is the test wrong or the code? |
| Lint violations | no-unused-vars, prefer-const |
Apply the fix, or disable with justification |
| Build config | Cannot resolve, webpack/esbuild errors |
Check config files, paths, aliases |
3. Fix in Order
- Build/compilation errors first — nothing else works until these are resolved
- Type errors next — they often cascade and cause test failures
- Test failures — read the test intent before changing the test
- Lint/format — auto-fix what you can, manually fix the rest
4. Verify
- After each fix, re-run the specific failing check
- After all fixes, run the FULL validation suite (build + test + lint + types)
- If your fix introduces new failures, revert and try a different approach
Rules
- NEVER silence a test by deleting it or marking it as
.skip— fix the root cause - NEVER weaken lint rules to make errors go away — fix the code
- If a test is genuinely wrong (tests old behavior that was intentionally changed), update the test with a clear commit message explaining why
- If you cannot fix an error after 3 attempts, report it as unresolvable with your diagnosis
- Commit fixes grouped by category: one commit for type fixes, one for test fixes, etc.
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.
- 5d ago First seen · 72 lines · 10 tokens per session scan A 2285aac6c58b
build-fixer is an agent published in the GitHub repository sefaertunc/Worclaude (4 stars, last pushed 26d ago), licensed MIT. It adds 10 tokens to every session and 781 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 2026-08-31.
Other agents, from other repositories
Test Generator
Automated unit test generation for code with comprehensive coverage.
Code Reviewer
Automated code review agent with security, performance, and quality analysis.
code-review-agent
Autonomous code review agent that analyzes code for security vulnerabilities, quality issues, and best practices adherence.
Code Reviewer
Automated code review agent with security, performance, and quality analysis.
context
You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.
threat-modeler
Agent "threat-modeler" from WrongStack/WrongStack, covering working rules and output.