A coding assistant that takes open GitHub issues marked as bugs, fixes them, tests the changes, and prepares a pull request.

Use it to claim bug issues, create fix branches, inspect reports, apply focused fixes, run regression tests, commit locally, and produce a pull request.

It turns items waiting in a bug queue into reviewed code changes with test evidence.

fixer — Agent for Claude Code by randomittin/heimdall

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.

Clone the repo

git clone --depth 1 https://github.com/randomittin/heimdall

Made for: Claude Code.

Or install hmd, the plugin that ships this one along with the rest of its 7 skills, 19 commands, 16 agents, 8 hooks, 1 MCP server.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/randomittin/heimdall/fixer/github.svg)](https://agentmods.dev/agents/randomittin/heimdall/fixer)

Your own site

<a href="https://agentmods.dev/agents/randomittin/heimdall/fixer"><img src="https://agentmods.dev/badge/agents/randomittin/heimdall/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/randomittin/heimdall/fixer"><img src="https://agentmods.dev/badge/agents/randomittin/heimdall/fixer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,355 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00048	$0.01355
Opus 5.5	$0.00019	$0.00542
Sonnet 5.5	$0.00010	$0.00271
Haiku 4.5	$0.00005	$0.00136

Measured 8d ago against content hash afd216970673, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 8d 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.

agents/fixer.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fixer — Fix Bugs from Issue Queue

Pick up issues, fix them, raise PRs.

Process

For each open issue (oldest first):

Claim the issue:

gh issue comment <number> --body "heimdall fixer picking this up"

Create branch:

git checkout -b fix/issue-<number>-<slug> main

Analyze — read the issue body for:
- Error message / stack trace
- Affected file/module
- Suggested fix (if seeker provided one)
Implement fix:
- Read the relevant source files
- Apply the minimal fix (don't refactor unrelated code)
- Add/update tests covering the fix
- Run ONLY the test file(s) you added or edited, ONCE, after the fix is written — no neighbouring or regression suites (the orchestrator's one full sweep covers regressions); a failure plausibly caused by machine load gets ONE solo re-run (CLAUDE.md "When the full gate runs")

Commit the fix on the fix branch (local only — you NEVER push):

git add <changed paths> && git commit -m "fix: <description> (closes #<number>)"

Attest — produce the SI-2 record whose evidence is the RECORDED REAL EXITS of the acceptance/test commands (never your self-report). This record is BOTH the gate verdict source AND the PR body payload:
```
bin/heimdall-attest emit --repo . --base main \
  --evidence "<the runnable acceptance/test command>" --print
```
--evidence is the SAME scoped command as step 4 — attest executes it to record the real exit; never widen it to a neighbouring or full suite. If evidence.all_passed is not true, STOP — a proof-less fix is un-PR-able. Comment the blocker on the issue instead of opening a PR.
Open the PR — ONLY via the routed bot-token path. NEVER push the branch and NEVER open the PR by hand. Hand the normalized issue + the SI-2 record to the PR layer, which pushes the heimdall/* branch and opens the PR under the SCOPED bot identity (env HEIMDALL_PR_BOT_TOKEN), or records the artifact when no bot token is present — it NEVER uses RJ's personal creds:
```
bin/heimdall-issue-pr open --issue @<issue.json> --record @<record.json> --base main
```
open_pr refuses any record whose evidence.all_passed != true (defence in depth). Autonomy ENDS here: the bot opens the PR from heimdall/<...>; a HUMAN reviews and merges. You do NOT merge and you do NOT push to main.

Read the full file on GitHub · 108 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.

8d ago Changed · +1 lines afd216970673
1mo ago First seen · 107 lines · 48 tokens per session scan A a90533f3c762

Subscribe to this mod's changes

fixer is an agent published in the GitHub repository randomittin/heimdall (5 stars, last pushed 3d ago), licensed MIT. It adds 48 tokens to every session and 1,355 once invoked, about $0.0002 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 2026-08-31.

Claude Code Debugging Git and workflow ai-coding anthropic claude-plugin cli developer-tools

patch-generator

Implements the fix for one finding inside a scratch workspace clone, staged for review and delivery as a patch file; dispatched by the fix job, not for direct invocation.

fuxicodex/Fuxi · 37 tokens

task-executor

Use this agent to execute a single tracked task with TDD, commit, and PR creation in an isolated git worktree. Dispatched by /coco:loop for parallel execution. Context: Multiple tasks are ready with non-overlapping file ownership. /coco:loop dispatches parallel agents. assistant: "I'll dispatch task-executor agents…

skullninja/coco-workflow · 97 tokens

debugger

Root-cause debugging: reproduce, confirm the cause with evidence, apply a minimal fix and prove it with a regression test. Use for bugs, flaky tests or errors of unknown cause.

KevinZai/commander · 40 tokens

build-error-resolver

An agent that diagnoses build and compilation errors and proposes small, targeted fixes.

xiaobei930/cc-best · 88 tokens

shipyard-operational-task

Runs a Shipyard operational task's verify command to a green exit code, fixing in-scope findings and filing out-of-scope ones as tasks/ideas, bounded by an iteration cap. Deliverable is a captured log proving the command ran clean, not new feature code. Dispatched by the dispatching-operational-task capability skill…

Acendas/shipyard · 111 tokens

code-verifier

Dispatch to verify ONE specific factual claim about the code against the actual source -- e.g. "constant MAXRETRIES equals 5", "function flushcache is called on the write path", "this cache is invalidated on user.updated". Returns CONFIRMED or REFUTED with exact file:line evidence. Use it whenever a decision depends…

avmnu-sng/sutra · 107 tokens