run-reviewable-subtask-loop

run-reviewable-subtask-loop is a skill for Claude Code from thienanblog/awesome-ai-agent-skills. It costs 83 tokens per session (4,301 once invoked), scanned A, original, Apache-2.0.

A workflow for delivering a large coding effort as a sequence of small, reviewable commits on one integration branch. Each unit is checked before it is combined with the rest.

In plain words
What is it for?
Use it for large plans that need ordered subtasks, per-step verification, focused combined checks, and a clear final publication decision.
Why use it?
It makes migrations, refactors, and roadmaps easier to review and recover when one part needs correction. It also requires explicit agreement before the workflow begins.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the project-development-skills plugin — 11 skills shipped together

Good fit Use it for large plans that need ordered subtasks, per-step verification, focused combined checks, and a clear final publication decision.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/thienanblog/awesome-ai-agent-skills/run-reviewable-subtask-loop
Install

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.

Any agent
npx skills add thienanblog/awesome-ai-agent-skills --skill run-reviewable-subtask-loop
Clone the repo
git clone --depth 1 https://github.com/thienanblog/awesome-ai-agent-skills

Made for: Claude Code.

Or install project-development-skills, the plugin that ships this one along with the rest of its 11 skills.

Wrote 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.

agentmods badge for run-reviewable-subtask-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/thienanblog/awesome-ai-agent-skills/run-reviewable-subtask-loop/github.svg)](https://agentmods.dev/skills/thienanblog/awesome-ai-agent-skills/run-reviewable-subtask-loop)
Your own site
<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.

agentmods 80×15 button for run-reviewable-subtask-loop

Your own site · 80×15
<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>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,301 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 12d ago against content hash 358ef1af252a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

plugins/project-development-skills/skills/run-reviewable-subtask-loop/SKILL.md · 373 lines

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.

  1. 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.
  2. 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.
  3. 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.
  4. 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.
  5. 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.

Read the full file on GitHub · 373 lines

Files

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.

Changes

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.

  1. 12d ago First seen · 373 lines · 83 tokens per session scan A 358ef1af252a

Subscribe to this mod's changes

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.