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 enrich-phase-plangit 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/enrich-phase-plan)<a href="https://agentmods.dev/skills/tonywu20/fortran-dev-pipeline/enrich-phase-plan"><img src="https://agentmods.dev/badge/skills/tonywu20/fortran-dev-pipeline/enrich-phase-plan/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/enrich-phase-plan"><img src="https://agentmods.dev/badge/skills/tonywu20/fortran-dev-pipeline/enrich-phase-plan.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 | $0.00098 | $0.02384 |
| Opus 5 | $0.00049 | $0.01192 |
| Sonnet 5 | $0.00020 | $0.00477 |
| Haiku 4.5 | $0.00010 | $0.00238 |
Grade A, and why
enrich-phase-plan 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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Enrich Phase Plan
Takes an approved high-level plan document and produces a detailed, executor-ready TOML implementation plan by running a pipeline of specialized agents over it.
Pipeline
fortran-architect (elaborate)
↓
plan-decomposer (break down into TOML)
↓
impl-plan-reviewer (review)
↓ [loop if Needs More Detail]
plan-decomposer (revise)
↓
dry-run compile (validate)
↓ [loop if fails, max 2]
fortran-architect (final review)
Step 1 — Identify the plan file
Ask the user for the path to the existing plan file if not already provided. Read it before proceeding.
Step 1.5 — Load deferred improvements and failure patterns (optional)
Deferred improvements: Search for deferred improvement files from prior phases:
fd deferred.md notes/pr-reviews/
If any are found, read them and include their contents in the fortran-architect elaboration prompt (Step 2) as additional context. This gives the architect visibility into improvements that were explicitly deferred — some may now be relevant to include.
Cross-round failure patterns: Search for fix plans from prior phases:
fd fix-plan.toml notes/pr-reviews/ | head -3
If any are found, read them and extract recurring issue categories. Look for patterns such as:
- Missing
use ModuleNamestatements (module wiring) - Missing
public ::declarations for symbols needed by other modules - Incomplete consumer updates (module created but never
used) - Stale
usestatements after refactoring - Cross-module integration failures (subroutine placed in wrong module)
Summarize the recurring categories as KNOWN_FAILURE_MODES. These will be passed to the plan-decomposer in Step 3 as proactive checks.
If no fix plans or deferred files exist, proceed without this context.
Step 2 — fortran-architect elaboration
Invoke the fortran-dev-pipeline:fortran-architect agent with this prompt:
You are reviewing the following implementation plan for the NEXT phase of work on a Fortran scientific codebase.
<plan>
{{PLAN_FILE_CONTENTS}}
</plan>
<deferred_improvements>
{{DEFERRED_CONTENTS — or "None" if no deferred.md files were found}}
</deferred_improvements>
Your job:
1. Identify what the next phase is trying to achieve.
2. Elaborate on implementation details that are underspecified — concrete subroutine signatures, INTENT declarations, MODULE locations, KIND parameters, error handling strategy (IOSTAT/STAT patterns).
3. Call out architectural cautions: numerical stability pitfalls, interface mismatches, module boundary violations, API surface decisions that are hard to reverse, places where the plan may conflict with Fortran idioms or the project's established patterns.
4. **Use LSP tools** to understand the current codebase state:
- Use `LSP documentSymbol` to locate existing modules/subroutines mentioned in the plan
- Use `LSP hover` to verify current subroutine signatures before proposing changes
- Use `LSP references` to understand how existing subroutines are called
- Use `LSP definition` to navigate to type/interface definitions
- Check `LSP diagnostics` to identify any existing issues that might affect the plan
5. Do NOT decompose into tasks. Output a single enriched narrative that a plan-decomposer agent can use as input.
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 · 242 lines · 98 tokens per session scan A b8560dcfbd1a
enrich-phase-plan is a skill published in the GitHub repository TonyWu20/fortran-dev-pipeline (5 stars, last pushed 4mo ago), licensed MIT. It adds 98 tokens to every session and 2,384 once invoked, about $0.0005 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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…