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 | $0.00083 | $0.04301 |
| Opus 5 | $0.00042 | $0.02150 |
| Sonnet 5 | $0.00017 | $0.00860 |
| Haiku 4.5 | $0.00008 | $0.00430 |
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 12d 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 — 373 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run Reviewable Subtask Loop
Deliver a large change as ordered, recoverable commits on a local integration branch. Review and verify every subtask before integration, then run focused aggregate checks and use one agreed aggregate publication path. After the work is complete, let the user decide whether to run a broader or full local suite.
Use task for the user's complete requested outcome, subtask for one independently reviewable and recoverable delivery unit, and phase only for an optional group of related subtasks. Do not use these terms interchangeably.
Enforce consent boundaries
- Apply this workflow only after the explicit opt-in described in the frontmatter. A routine implementation plan, silence, or a general request to start coding is not acceptance.
- Treat a subtask as a delivery and recovery boundary, not a delegated worker. Perform implementation, self-review, verification, and finalization sequentially in the main conversation by default.
- Do not infer delegation approval from terms such as subtask, phase, review, reviewer, parallelizable, execute the plan, or use this skill. Before any delegation, explain why it helps, its usage impact, and the proposed agent count and scope, maximum concurrency, and roles. Obtain explicit approval and ask again before expanding the approved count, concurrency, roles, or scope.
- Treat Remote CI as a separate consent boundary. Reading repository workflow files is always local discovery; triggering remote jobs requires explicit authorization for the current series and trigger. Read references/remote-ci.md when Remote CI is required, requested, or could start automatically.
- Treat planning as read-only except for exact temporary plan artifacts the user requested or the durable-plan mode selected under the criteria below. Create branches, commits, merges, pushes, review requests, or branch deletions only when the user's execution request or repository workflow authorizes them. Never infer final-merge authorization from permission to implement or publish.
What ships with it
3 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.
- 12d 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 (65 stars, last pushed 14d ago), licensed Apache-2.0. It adds 83 tokens to every session and 4,301 once invoked, about $0.0004 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
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for prisma-next. 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 repo-sync on macOS for shared documents and team context. Use when asked what repo-sync does, to automatically sync a repo, add a repo to repo-sync, stop syncing or un-sync a repo, check sync health, configure repo-sync, uninstall it, or install and maintain its bundled agent skill. Ordinary one-time Git pulls…
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
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…
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.