A guided workflow for taking a GitHub bug report from investigation through a tested fix and pull request. It checks for duplicates, reproduces the problem, records before-and-after evidence, and asks for approval before opening the PR.

Use it to investigate an issue, write a regression test, implement and validate the fix, and create a pull request with before-and-after recordings.

It keeps the steps of a bug fix connected and gives reviewers comparable proof that the problem is resolved. This reduces repeated manual work and helps prevent unverified fixes from reaching review.

fix-issue — Skill for Claude Code by tomzx/agents

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.

Any agent

npx skills add tomzx/agents --skill fix-issue

Clone the repo

git clone --depth 1 https://github.com/tomzx/agents

Made for: Claude Code.

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/skills/tomzx/agents/fix-issue/github.svg)](https://agentmods.dev/skills/tomzx/agents/fix-issue)

Your own site

<a href="https://agentmods.dev/skills/tomzx/agents/fix-issue"><img src="https://agentmods.dev/badge/skills/tomzx/agents/fix-issue/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/skills/tomzx/agents/fix-issue"><img src="https://agentmods.dev/badge/skills/tomzx/agents/fix-issue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,934 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	$0.00034	$0.01934
Opus 5.5	$0.00014	$0.00774
Sonnet 5.5	$0.00007	$0.00387
Haiku 4.5	$0.00003	$0.00193

Measured 22d ago against content hash e3fe85541966, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fix-issue 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 22d 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.

skills/fix-issue/SKILL.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fix Issue

Orchestrates a bug fix from issue to PR by delegating to specialized skills:

check-duplicates -- search for duplicate issues and existing fix PRs
reproduce-issue -- fetch the issue, create a worktree, reproduce the bug, record a "before" video of the defect, post results
create-implementation -- write a regression test, implement the fix, verify tests pass
validate-implementation -- replay the before-command on the fixed code to capture a comparable "after" recording, then present the before/after pair for user sign-off before any PR is opened
create-pr -- push the branch and open a pull request, embedding the pre-captured before/after pair in a side-by-side section

The before recording (and the manifest naming the demonstration command/URL) flows from reproduce-issue to validate-implementation via /tmp/<owner>/<repo>/<issue-id>/. validate-implementation replays the same command/URL on the fixed code so the two recordings are directly comparable, then writes captured-proof.json, which create-pr consumes. Recording happens before PR creation, at human-review time, so the user can confirm the fix before it is posted.

If duplicates are found or reproduction fails, the workflow stops at the relevant step.

Prerequisites

Apply the shared SDLC conventions in skills/sdlc/references/shared.md.
If no argument is provided, target the issue from $ISSUE_NUMBER (and $REPO).
gh CLI authenticated with write access to the target repository
A GitHub issue number describing a bug
Git worktree support (git worktree available)
Read any files present under .sdlc/context/ and apply any artifact style rules found there

Workflow

/check-duplicates
        |
        v
Duplicates found?
   /          \
 No             Yes
  |              |
  v              v
/reproduce-      Stop
issue            (comment posted)
        |
        v
Reproduced?
   /          \
 Yes            No
  |              |
  v              v
Record before   Stop
(video + manifest (comment posted)
 to /tmp/<owner>/<repo>/<issue-id>/)
        |
        v
/create-implementation
        |
        v
/validate-implementation
(replays before-command on fixed code,
 captures after, presents pair, gets sign-off)
        |
        v
/create-pr
(embeds pre-captured before/after pair)
        |
        v
Done (PR ready for review)

Read the full file on GitHub · 210 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.

22d ago Changed · +11 lines e3fe85541966
24d ago Changed 14c6166ce8ea
1mo ago First seen · 199 lines · 34 tokens per session scan A dfa57ada868c

Subscribe to this mod's changes

fix-issue is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 1,934 once invoked, about $0.0001 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 2026-09-03.

Debugging Git and workflow

agent-merge-conflict-arbiter

Neutral arbiter for merge conflicts between two agents.

NousResearch/hermes-agent · 19 tokens

git-advanced-workflows

Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.

wshobson/agents · 54 tokens

enable-check-includes-strict

Enable and migrate Chromium targets and directories to checkincludesstrict = true, diagnosing and resolving header include violations as part of the checkincludesstrict LSC. Use when adding directories to the allowlist, enabling strict header checks on targets, or resolving CHECKINCLUDESSTRICTUNTRIAGED targets.

chromium/chromium · 70 tokens

resolve-handoff

Emit the complete Resolve handoff with exact modes, outcomes, test evidence, and publication state.

omnigent-ai/omnigent · 23 tokens

reproduce-and-fix-issues

Reproduce triaged Slack bugs through a configured app-control adapter, verify existing fixes, and open a bounded draft pull request only after before-and-after proof. Use only from the configured Benny repro automation.

backnotprop/pstack · 48 tokens

cy-orquestrate-issue

Orchestrate GitHub bug resolution through a new CompozyOS managed worktree and Claude Opus 5.5 Medium session per issue. Investigate reported bugs, create missing issues, and dispatch an executor responsible for a detailed PR, green CI, and all CodeRabbit and Greptile feedback. Use when asked to delegate issue…

compozy/compozy · 94 tokens