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 TonyWu20/fortran-dev-pipeline --skill plan-reviewgit clone --depth 1 https://github.com/TonyWu20/fortran-dev-pipelineWrote 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/tonywu20/fortran-dev-pipeline/plan-review)<a href="https://agentmods.dev/skills/tonywu20/fortran-dev-pipeline/plan-review"><img src="https://agentmods.dev/badge/skills/tonywu20/fortran-dev-pipeline/plan-review/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/tonywu20/fortran-dev-pipeline/plan-review"><img src="https://agentmods.dev/badge/skills/tonywu20/fortran-dev-pipeline/plan-review.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 | $0.00072 | $0.01063 |
| Opus 5 | $0.00036 | $0.00531 |
| Sonnet 5 | $0.00014 | $0.00213 |
| Haiku 4.5 | $0.00007 | $0.00106 |
Grade A, and why
plan-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Review Skill
Reviews a phase plan for soundness before implementation starts. Validates the design, incorporates deferred improvements from prior phases, and produces a decision log. This is Gate 1 — run it after /next-phase-plan and before /enrich-phase-plan.
Trigger
/plan-review [plan-path]
If no path is given, ask the user.
Command-line Tools
- use
fdinstead offind - use
rginstead ofgrep
Process
Step 1: Identify Inputs
-
Phase plan: If
[plan-path]was given, read it. Otherwise ask the user:"Which plan file should I review? (e.g.,
plans/phase-4/PHASE_PLAN.md)"Read the full plan content.
-
Deferred improvements (from prior phases):
fd deferred.md notes/pr-reviews/- If one or more
deferred.mdfiles are found, list them to the user and read all of them. Include their contents in the review. - If none exist, proceed without deferred context.
- If one or more
-
Project memory (always):
MEMORY_DIR="$HOME/.claude/projects/$(pwd | sd '/' '-')/memory"Read
$MEMORY_DIR/MEMORY.mdand every linked memory file.
Step 2: fortran-architect Review
Pass everything to the fortran-dev-pipeline:fortran-architect agent with this prompt:
You are performing a pre-implementation architectural review of a Fortran scientific project.
<phase_plan>
{{PLAN_CONTENTS}}
</phase_plan>
<deferred_improvements>
{{DEFERRED_CONTENTS — or "None" if no deferred.md files were found}}
</deferred_improvements>
<project_memory>
{{MEMORY_CONTENTS}}
</project_memory>
Answer these three questions:
1. **Design soundness**: Does this plan produce a sound design?
- Are there architectural gaps the plan doesn't address?
- Are there numerical stability pitfalls, interface mismatches, or API decisions that are hard to reverse?
- Are there missing error handling strategies or module boundary violations?
- Are there INTENT declaration patterns, KIND parameter conventions, or interface requirements implied but not stated?
- If the plan looks sound, say so explicitly.
2. **Deferred item decisions**: For each item in `<deferred_improvements>`, decide:
- **Absorb** — incorporate it into this plan (specify which section to update and how)
- **Defer again** — not yet warranted (specify a concrete updated precondition)
- **Close** — not worth doing (explain why)
3. **Recommended plan amendments**: List concrete additions or changes to the plan, if any. If no changes are needed, state "No amendments required."
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.
- 11d ago First seen · 137 lines · 72 tokens per session scan A 50c1782f8d86
plan-review is a skill published in the GitHub repository TonyWu20/fortran-dev-pipeline (5 stars, last pushed 4mo ago), licensed MIT. It adds 72 tokens to every session and 1,063 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 2026-08-31.
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…