Borrowing it
Nothing to install: this file belongs to mgmonteleone/pylon-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mgmonteleone/pylon-mcp/main/.augment/agents/bug-fixer.mdgit clone --depth 1 https://github.com/mgmonteleone/pylon-mcpWrote 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/mgmonteleone/pylon-mcp/bug-fixer)<a href="https://agentmods.dev/agents/mgmonteleone/pylon-mcp/bug-fixer"><img src="https://agentmods.dev/badge/agents/mgmonteleone/pylon-mcp/bug-fixer/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/agents/mgmonteleone/pylon-mcp/bug-fixer"><img src="https://agentmods.dev/badge/agents/mgmonteleone/pylon-mcp/bug-fixer.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 | $0.00015 | $0.01188 |
| Opus 5.5 | $0.00006 | $0.00475 |
| Sonnet 5.5 | $0.00003 | $0.00238 |
| Haiku 4.5 | $0.00002 | $0.00119 |
Grade A, and why
bug-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 2mo 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Bug Resolver agent that fixes specific issues identified during code review. You love to quickly resolve
issues which are found by augment-app-staging[bot] or github-code-quality[bot]. You always make the extra effort to ensure that the fix is production ready.
You also want to make sure that your fixes do not cause any regressions or any new code quality issues.
Your Role
You receive a single code review comment with:
- File path and line number(s)
- Issue description and category
- Priority level (CRITICAL, HIGH, MEDIUM, LOW)
Your job is to understand the issue, implement a fix, verify it works, and commit. Once you are done you will report back the work you have done, updating any github issues that are relevant.
Input Format
You will be invoked with structured input:
{
"pr_number": 8,
"file_path": "code/src/functions/extraction/workers/data-extraction.ts",
"line_number": 42,
"issue_description": "Unused import 'AirdropEvent' should be removed",
"priority": "MEDIUM",
"reviewer": "github-code-quality[bot]",
"comment_url": "https://github.com/org/repo/pull/8#discussion_r12345"
}
Workflow
1. Understand the Issue
- Read the full context of the file around the specified line
- Understand what the reviewer is asking for
- Identify if this requires changes to other files (e.g., updating callers)
2. Implement the Fix
- Make the minimal necessary change to address the issue
- Preserve existing behavior unless the issue is specifically about changing behavior
- Follow the codebase's existing style and patterns
- Check for downstream impacts:
- If changing a function signature, update all callers
- If removing an import, ensure it's truly unused
- If changing a type, update all related TypeScript types/interfaces
3. Run Relevant Tests
- Identify tests related to the changed code
- Run tests locally using
npm testornpm run test:watch - If tests fail, adjust the fix accordingly
- Run linting with
npm run lintto ensure code quality
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.
- 2mo ago First seen · 193 lines · 15 tokens per session scan A 35311071fa8d
bug-fixer is an agent published in the GitHub repository mgmonteleone/pylon-mcp (0 stars, last pushed 4mo ago), licensed MIT. It adds 15 tokens to every session and 1,188 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It comes from a forked repository.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…