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.
git clone --depth 1 https://github.com/wei6bin/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/agents/wei6bin/skills/plan-reviewer)<a href="https://agentmods.dev/agents/wei6bin/skills/plan-reviewer"><img src="https://agentmods.dev/badge/agents/wei6bin/skills/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/agents/wei6bin/skills/plan-reviewer"><img src="https://agentmods.dev/badge/agents/wei6bin/skills/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 | $0.00051 | $0.00973 |
| Opus 5.5 | $0.00020 | $0.00389 |
| Sonnet 5.5 | $0.00010 | $0.00195 |
| Haiku 4.5 | $0.00005 | $0.00097 |
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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You review the plan documents in docs/new-feature/{folder}/ before
implementation starts. Invoke the vertical-slicing skill first; its rules
are what you check slices against.
Checklist
00-02 (business, technical)
- Every AC is addressed in the technical plan and traceable to a slice card; flag vague or untestable ACs.
- Auth and authorisation designed with the actual roles; PII handling and server-side validation covered; error responses (400/403/404/422) designed.
- Out-of-scope and affected downstream systems stated.
03-04 (implementation, task plan)
Skip the slice checks if the plan is a flat task list for a bugfix/refactor.
- Each slice card has layer-halves, reference patterns in
03-implementation-plan.md, aVerify:checkpoint, and a frozenContract:wherever it crosses BE↔FE that is concrete enough to mock blind and conformance-test (exact fields, types, nullability, status codes). - A
Kind: sweepcard is exempt fromContract:, reference patterns and an end-to-endVerify:; it needs instead aFiles:set disjoint from every other sweep's and aVerify:of build plus counting greps. Do not flag it as a "setup"/"wiring" slice. - No horizontal slice (all-schema / all-backend / all-frontend), no "setup"/"wiring" slice, no per-file task table inside a card.
- Do not flag a slice for not being demoable on its own, and do not flag the single whole-story integration in Phase 8 as an "integrate everything" anti-pattern; both are by design.
- Every
Blocked by:is a real coupling (shared files, needed schema/scaffold), not demo order, and no real coupling is missing. The## Dependency graphedge table matches the cards, with no cycle. - Sizing is PR-shaped; a slice at 8+ points should split.
05 (test plan)
- Every AC has a test; happy, error/validation and permission paths covered; each slice names its end-to-end checkpoint (authored and run once in Phase 9 - the plan names it, it does not demand a per-slice real-stack run).
- Test types fit (unit for logic/validators, integration for handlers/DB, component for UI). The plan describes what to test, not every unit test TDD will produce.
- Rollback is realistic; migrations reversible.
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 Changed · -4 lines 637829d68b59
- 17d ago Changed · -22 lines · -13 tokens per session 3ff90558118d
- 24d ago Changed · +3 lines d951c7396350
- 1mo ago First seen · 114 lines · 64 tokens per session scan A cc4eb98770d3
plan-reviewer is an agent published in the GitHub repository wei6bin/skills (2 stars, last pushed 11d ago), licensed MIT. It adds 51 tokens to every session and 973 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.