Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/sfc-gh-myoung/ai_coding_rulesnpx agentmods add skills/sfc-gh-myoung/ai_coding_rules/plan-reviewerWrote 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/sfc-gh-myoung/ai_coding_rules/plan-reviewer)<a href="https://agentmods.dev/skills/sfc-gh-myoung/ai_coding_rules/plan-reviewer"><img src="https://agentmods.dev/badge/skills/sfc-gh-myoung/ai_coding_rules/plan-reviewer/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/sfc-gh-myoung/ai_coding_rules/plan-reviewer"><img src="https://agentmods.dev/badge/skills/sfc-gh-myoung/ai_coding_rules/plan-reviewer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00040 | $0.02342 |
| Opus 5 | $0.00020 | $0.01171 |
| Sonnet 5 | $0.00008 | $0.00468 |
| Haiku 4.5 | $0.00004 | $0.00234 |
Grade A, and why
plan-reviewer 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 10d 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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Reviewer
Quick Start
target_file: plans/my-plan.md
review_mode: FULL
Output: reviews/plan-reviews/<plan-name>-<model>-<date>.md
Purpose
Review LLM-generated plans for autonomous agent executability using an 8-dimension rubric optimized for Priority 1 compliance (Agent Understanding).
Plans are scored on whether autonomous agents can execute them without judgment calls or clarification requests.
Use this skill when
- Review a plan file for agent executability
- Compare multiple plans for the same task (choose winner)
- Conduct meta-review to analyze consistency across reviews
- Verify plan meets Priority 1 compliance before execution
What NOT to Use This For
- General documentation review → Use
doc-reviewerinstead - Rule file validation → Use
rule-reviewerinstead - Code review → Use standard code review tools
- Task execution → This skill evaluates plans, it doesn't execute them
Inputs
Required:
- review_mode:
FULL|COMPARISON|META-REVIEW|DELTA - target_file(s): Path(s) to plan file(s) - varies by mode
Mode-specific:
| Mode | Required Input | Description |
|---|---|---|
| FULL | target_file |
Single plan file path |
| COMPARISON | target_files |
List of plan file paths |
| META-REVIEW | review_files |
List of review file paths |
| DELTA | target_file + baseline_review |
Current plan + prior review |
Optional:
output_root: Output directory (default:reviews/)execution_mode:parallel(default, 8 sub-agents) orsequentialtiming_enabled: Enable execution timing (default:true— v2.5.0 universal default; setfalseto opt out withnot-requestedrow)overwrite: Overwrite existing files (default:false)
Review Modes
| Mode | Purpose | Output Location |
|---|---|---|
| FULL | Comprehensive single-plan review | {root}/plan-reviews/<name>-<model>-<date>.md |
| COMPARISON | Rank multiple plans, declare winner | {root}/summaries/_comparison-*.md |
| META-REVIEW | Analyze consistency across reviews | {root}/summaries/_meta-*.md |
| DELTA | Track issue resolution from baseline | {root}/plan-reviews/<name>-delta-*.md |
What ships with it
36 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.
- CHANGELOG.md 977 B
- examples/comparison-review.md 5.5 KB
- examples/edge-cases.md 6.4 KB
- examples/full-review.md 7.0 KB
- examples/meta-review.md 7.0 KB
- rubrics/_overlap-resolution.md 4.7 KB
- rubrics/completeness.md 26 KB
- rubrics/context.md 24 KB
- rubrics/decomposition.md 22 KB
- rubrics/dependencies.md 23 KB
- rubrics/executability.md 33 KB
- rubrics/risk-awareness.md 30 KB
- rubrics/scope.md 26 KB
- rubrics/SCORING.md 4.4 KB
- rubrics/success-criteria.md 30 KB
- tests/test-inputs.md 5.2 KB
- tests/test-invocation-comparison.md 4.2 KB
- tests/test-invocation-full.md 3.6 KB
- tests/test-modes.md 5.8 KB
- tests/test-outputs.md 5.6 KB
- tests/TESTING.md 6.2 KB
- workflows/consistency-check.md 7.0 KB
- workflows/delta-review.md 6.9 KB
- workflows/determinism.md 5.7 KB
- workflows/dimension-subagent-template.md 8.4 KB
- workflows/error-handling.md 3.0 KB
- workflows/file-write.md 7.8 KB
- workflows/input-validation.md 1.8 KB
- workflows/issue-inventory.md 7.6 KB
- workflows/model-slugging.md 1.1 KB
- workflows/overlap-validator.md 14 KB
- workflows/parallel-execution.md 15 KB
- workflows/parallel-specs.md 8.8 KB
- workflows/parameter-collection.md 12 KB
- workflows/review-execution.md 22 KB
- workflows/score-aggregation.md 12 KB
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.
- 10d ago First seen · 217 lines · 0 tokens per session scan A da7ac8c86f45
plan-reviewer is a skill published in the GitHub repository sfc-gh-myoung/ai_coding_rules (7 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 40 tokens to every session and 2,342 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…