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.
npx skills add richkuo/rk-skills --skill work-on-issue-loopgit clone --depth 1 https://github.com/richkuo/rk-skillsWrote 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/skills/richkuo/rk-skills/work-on-issue-loop)<a href="https://agentmods.dev/skills/richkuo/rk-skills/work-on-issue-loop"><img src="https://agentmods.dev/badge/skills/richkuo/rk-skills/work-on-issue-loop/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.
<a href="https://agentmods.dev/skills/richkuo/rk-skills/work-on-issue-loop"><img src="https://agentmods.dev/badge/skills/richkuo/rk-skills/work-on-issue-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00147 | $0.01775 |
| Opus 5 | $0.00073 | $0.00888 |
| Sonnet 5 | $0.00029 | $0.00355 |
| Haiku 4.5 | $0.00015 | $0.00178 |
Grade A, and why
work-on-issue-loop 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 today.
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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
work-on-issue-loop
Drive an issue from "validated" to "PR reviewed to convergence" without stopping. Step 1 implements the issue and opens the PR; the review cycle after that is fix-pr-review-loop's convergence loop run against the new PR. fix-pr-review-loop owns the loop mechanics (bot selection, preflight, wait, stop conditions, cycle cap, resolution, terminal table). This skill adds the implementation step, the follow-on issue sweep, and a terminal state for a run that never produces a PR. With an existing PR and no issue to implement, use fix-pr-review-loop directly.
Input
- Nothing — the issue validated or planned this session; with none, stop and ask which issue. Never select an issue from a list.
#<N>/<N>/ URL /owner/repo#N.- Optional
targetBranch({ issue, targetBranch }or a prose "target branch "): passed unchanged towork-on-issue. The review loop follows the PR's own base branch.
Steps
1. Implement, open the PR, and trigger the first review
Invoke the work-on-issue skill (Skill tool, skill: work-on-issue), passing the resolved issue number explicitly. It implements, verifies, commits, pushes, and opens the PR (Closes #<N>). It never requests review; that is this loop's job. Gate on its outcome:
- Stopped with no PR (closed issue, existing PR, wrong repo, or any other stop
work-on-issuedefines; it owns the list) → nothing to drive; stop and relay its report with its stop reason. - PR opened → capture the PR number/URL and branch, then post the first trigger yourself as a separate one-line comment with no footer:
gh pr comment <PR-number> --body "<band-derived trigger>". Do not wait on CI; the reviewer surfaces check failures itself. Match the repo's trigger phrase if recent PR comments show it differs.
Which trigger. validate-issue step 6 owns the first-review table with its Claude and Codex columns; this file states no boundary of its own. The score source is the issue just implemented: a stamped PR review: line in its Execution block overrides the band, else its [C<score>] title prefix. A missing score routes to the heaviest row.
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.
- today Changed 30d860d96f49
- 2d ago Changed · -11 lines 7c73639c62a8
- 3d ago Changed d7104eb3d2d8
- 5d ago Changed · +1 lines 84f4edcf4338
- 9d ago First seen · 81 lines · 147 tokens per session scan A 359c7ea09895
work-on-issue-loop is a skill published in the GitHub repository richkuo/rk-skills (49 stars, last pushed today), licensed MIT. It adds 147 tokens to every session and 1,775 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
issue-fields-migration
Bulk-migrate metadata to GitHub issue fields from two sources: repo labels (e.g. priority labels to a Priority field) and Project V2 fields. Use when users say "migrate my labels to issue fields", "migrate project fields to issue fields", "convert labels to issue fields", "copy project field values to issue fields"…
comet-github-idea-to-issue
A workflow for turning a local idea, bug observation, or improvement proposal into a focused GitHub Issue draft. GitHub Issues are shared records for bugs, features, questions, and maintenance work.
codex-issue-coordinator
Coordinates a large batch of GitHub issues through separate Codex worker threads, tested pull requests, review loops, and gated merges. Use when the user asks one Codex thread to manage several coding sessions or complete a parent issue, milestone, or issue batch.
loop-it
An automated workflow that repeatedly fetches open GitHub issues, orders them by dependencies, implements them, reviews the changes, and ships them.
to-issues
A planning aid that breaks a PRD or technical specification into small implementation issues, each covering a complete, demonstrable piece of work.
friction-log
File contributor or agent papercuts as GitHub issues labeled friction, or investigate those issues as the daily friction-log Cloud Agent. Use when you hit repo friction, when asked to log friction, or when spawned to resolve open friction issues.