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 thienanblog/awesome-ai-agent-skills --skill run-reviewable-subtask-loopgit clone --depth 1 https://github.com/thienanblog/awesome-ai-agent-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/thienanblog/awesome-ai-agent-skills/run-reviewable-subtask-loop)<a href="https://agentmods.dev/skills/thienanblog/awesome-ai-agent-skills/run-reviewable-subtask-loop"><img src="https://agentmods.dev/badge/skills/thienanblog/awesome-ai-agent-skills/run-reviewable-subtask-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/thienanblog/awesome-ai-agent-skills/run-reviewable-subtask-loop"><img src="https://agentmods.dev/badge/skills/thienanblog/awesome-ai-agent-skills/run-reviewable-subtask-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 | $0.00044 | $0.01122 |
| Opus 5.5 | $0.00018 | $0.00449 |
| Sonnet 5.5 | $0.00009 | $0.00224 |
| Haiku 4.5 | $0.00004 | $0.00112 |
Grade A, and why
run-reviewable-subtask-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 27d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run Reviewable Subtask Loop
Deliver coherent, recoverable increments and review the aggregate result before publication.
Delegation
Run in the main conversation by default. Delegation can increase usage: obtain explicit approval for the proposed agent count and scope before using subagents. Reuse that approval within its bounds; ask again before expanding the approved count or scope.
Establish the series
Inspect repository instructions, working-tree and worktree state, the intended base and its fetched remote counterpart, and relevant delivery checks. Follow repository freshness policy; preserve the intended base and user changes. Do not silently merge, rebase, reset, or overwrite work to make the starting state convenient.
Resolve the branch, commit, push, PR, merge, and cleanup permissions from the user's request. A request to implement does not automatically authorize publication or final merge. Ask only about missing permissions when needed, after completing independent preparatory work.
Use one integration branch and sequential commits by default. Use temporary subtask branches when repository policy or an actual isolation/recovery need justifies them. Never check out the same branch in two worktrees. Record initial base and integration SHAs and the exact branches created by this series.
Inspect remote triggers before publication. Read remote-ci.md when push, PR, or merge can start CI. Honor explicit local-only, cost, and separate-approval requirements.
Keep a compact ledger
Use the conversation or an existing project progress surface. Persist a plan only when requested or needed for recovery across sessions; use the repository's established location. Record exact task-owned artifact paths and preserve them according to the user's retention preference.
For each subtask, track its responsibility, acceptance criteria, dependencies, focused checks, status, and resulting commit. Add findings, evidence, and recovery points as they exist.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 27d ago Changed · -1 lines · -2 tokens per session 824c492aa2e3
- 1mo ago Changed · -307 lines · -37 tokens per session 3edd220d5e9a
- 1mo ago First seen · 373 lines · 83 tokens per session scan A 358ef1af252a
run-reviewable-subtask-loop is a skill published in the GitHub repository thienanblog/awesome-ai-agent-skills (70 stars, last pushed 27d ago), licensed Apache-2.0. It adds 44 tokens to every session and 1,122 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 2026-08-30.
Other skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.
git-commit
Generate well-formatted git commit messages following conventional commit standards.
repo-sync
Manage automatic Git syncing on macOS with repo-sync. Use only when the user explicitly invokes /repo-sync.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
engineer-bot-ops
A workflow for carrying an engineering task from scope through implementation and reviewable delivery. It works with a repository's branch, existing changes, rules, checks, and permissions while separating completed, unverified, and next-step work.
contributing
How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…