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.
git clone --depth 1 https://github.com/xbim08/awesome-claude-code-pluginsWrote 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/commands/xbim08/awesome-claude-code-plugins/github-issue-fix)<a href="https://agentmods.dev/commands/xbim08/awesome-claude-code-plugins/github-issue-fix"><img src="https://agentmods.dev/badge/commands/xbim08/awesome-claude-code-plugins/github-issue-fix.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 | $0.00022 | $0.01303 |
| Opus 5 | $0.00011 | $0.00651 |
| Sonnet 5 | $0.00004 | $0.00261 |
| Haiku 4.5 | $0.00002 | $0.00130 |
Grade A, and why
github-issue-fix 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 3d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Please analyze and fix the GitHub issue: $ARGUMENTS.
Follow these steps:
PLAN
-
Use
gh issue viewto get the issue details- Fetch the full description, labels, assignees, and any metadata from the GitHub issue.
-
Read and understand the problem described in the issue
- Carefully analyze the main problem statement and what outcome is expected.
-
Identify related or linked sub-issues and dependencies
- Look for:
- Child issues or tasks linked under the main issue (e.g., checklists in the issue body such as
- [ ] Create DB schema,- [ ] Implement API). - Related GitHub issues linked as "blocks", "is blocked by", or "relates to".
- Issues grouped under an epic or parent story, if using project management tools.
- Child issues or tasks linked under the main issue (e.g., checklists in the issue body such as
- Treat these sub-issues as part of the scope. If they exist, factor them into the plan so the solution is efficient and avoids duplication.
- Example:
- Main Issue: "Implement user authentication"
- Sub-issues found:
#201Setup user database schema#202Create login API#203Integrate OAuth provider
- Plan must account for all three, because they are part of solving the main issue.
- Look for:
-
Ask clarification questions if needed
- If any detail is unclear, prepare a list of clarification questions for the issue author or stakeholders.
-
Understand the prior art for the issue
- Search scratchpads or internal documentation for previous thoughts related to the issue.
- Search previous PRs to see if any work was already attempted on this problem.
- Search the codebase for relevant files, functions, or modules that may already contain related logic.
-
Ultrathink about how to solve the issue in a small and manageable way
- Break down the main issue and its sub-issues into smaller, actionable tasks.
- Sequence the tasks in a logical order, respecting dependencies (e.g., database before API, API before UI).
- Draft a clear plan with todos that can be executed incrementally.
-
Document the plan in the scratchpad
- Include the issue name in the filename for easy reference.
- Add the direct link to the issue in the scratchpad.
- Ensure the plan is well-structured so it can be executed by another human or an automated system without requiring extra context.
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.
- 3d ago First seen · 153 lines · 22 tokens per session scan A bdf5ec171f40
github-issue-fix is a command published in the GitHub repository xbim08/awesome-claude-code-plugins (10 stars, last pushed yesterday), licensed Apache-2.0. It adds 22 tokens to every session and 1,303 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 2026-09-04.
Other commands, from other repositories
claudex
Claude writes, Codex reviews, iterate until both agree — then ship with love.
verdict
Two-model verdict — Claude and Codex independently review the same diff, disagreements surfaced.
setup
Verify ClauDex prerequisites — Codex CLI, authentication, and git.
analyze-issue
Fetches GitHub issue details to create comprehensive implementation specifications, analyzing requirements and planning structured approach with clear implementation steps.
code-review
Perform a comprehensive code review of recent changes.
bug-fix
Streamlines bug fixing by creating a GitHub issue first, then a feature branch for implementing and thoroughly testing the solution before merging.