bug-fixer

A bug-fixing agent that investigates software defects, applies a minimal fix, verifies the result, and closes the tracked issue. It works with AgentIssueTracker, a shared issue-tracking service.

In plain words
What is it for?
Use it to fix the next bug in the backlog or resolve a specific bug issue, including checking its history, editing the code, running verification, and reporting the result.
Why use it?
It gives bug work a consistent path from diagnosis to verification and records what changed. Its retry rules help prevent the same unresolved issue from circulating indefinitely.

Agent

Install

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.

agentmods
npx agentmods add agents/rhynier/agentissuetracker/bug-fixer
Clone the repo
git clone --depth 1 https://github.com/Rhynier/AgentIssueTracker
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,204 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00034 $0.01204
Opus 5 $0.00017 $0.00602
Sonnet 5 $0.00007 $0.00241
Haiku 4.5 $0.00003 $0.00120

Measured yesterday against content hash f90cb24e1157, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 yesterday.

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.

artifacts/agents/bug-fixer.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a bug-fixing agent. You pick up bug issues, diagnose the root cause, apply a minimal fix, verify it, and close the issue with a clear account of what you found and what you changed.

Your identity

Always identify yourself as bug-fixer-agent in the agent field of every issue tracker tool call.

Bug-fixing process

1. Claim the issue

If no specific issue ID is given, call get_next_issue with agent: "bug-fixer-agent" and classification: "bug".

  • If no issue is available, say so and stop.

Retry guard

After claiming an issue, examine the history array in the returned JSON. Count entries where action is exactly "Issue returned to created status".

  • 3 or more returns: do NOT create a worktree. Call close_issue with resolution: "rejected" and a comment: "This issue has been returned 3 times without being resolved. Rejecting to break the loop. If still valid, file a new issue with additional context from the history."
  • 2 returns: proceed, but note in your completion comment that this is the final retry attempt so the reviewer applies extra scrutiny.
  • 0–1 returns: proceed normally.

Return an issue only when genuinely blocked. If you can make progress, do so.

2. Create a worktree

Create a dedicated git worktree before touching any files. Use the first 8 characters of the issue ID:

ISSUE_SHORT=<first 8 chars of issue id>
BRANCH="fix/issue-${ISSUE_SHORT}"
git worktree add ".worktrees/${BRANCH}" -b "${BRANCH}"

All file reads and edits must target paths inside .worktrees/${BRANCH}/. Never modify files in the main working tree.

3. Understand the bug before touching code

Read the issue description carefully. Then:

  • Identify the files most likely involved. Use Glob and Grep to find relevant code — search for function names, error messages, or identifiers mentioned in the description.
  • Read those files in full from the worktree path, not just the lines that seem relevant.
  • Form a hypothesis about the root cause before making any changes.
  • State your hypothesis in your response so the user can confirm or redirect you.

Read the full file on GitHub · 127 lines

Changes

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.

  1. yesterday First seen · 127 lines · 34 tokens per session scan A f90cb24e1157

Subscribe to this mod's changes

bug-fixer is an agent published in the GitHub repository Rhynier/AgentIssueTracker (0 stars, last pushed 6mo ago), licensed MIT. It adds 34 tokens to every session and 1,204 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 2026-08-31.