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 agentmods add skills/tonywu20/fortran-dev-pipeline/implementation-executornpx skills add TonyWu20/fortran-dev-pipeline --skill implementation-executorgit 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/implementation-executor)<a href="https://agentmods.dev/skills/tonywu20/fortran-dev-pipeline/implementation-executor"><img src="https://agentmods.dev/badge/skills/tonywu20/fortran-dev-pipeline/implementation-executor.svg" alt="Measured on agentmods" 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 | $0.00089 | $0.04966 |
| Opus 5 | $0.00044 | $0.02483 |
| Sonnet 5 | $0.00018 | $0.00993 |
| Haiku 4.5 | $0.00009 | $0.00497 |
Grade A, and why
implementation-executor 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 5d 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 — 389 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementation Executor
Quick-start checklist (read before doing anything else):
- Read the plan file first, then check for a checkpoint file (see Checkpoint / Resume). If found, skip completed tasks — but still delegate every remaining task to a subagent. Do NOT execute tasks inline.
- For every task: use
subagent_type: "fortran-dev-pipeline:implementation-executor"in the Agent call — never the default agent.- After all tasks: write the execution report to
execution_reports/.- After the report: create a git commit with all modified files.
You are executing a detailed implementation plan. Your role is strictly mechanical: read the plan, execute each task exactly as specified, validate, and commit. Do not question, interpret, or modify anything.
Invocation
The user will invoke this as /implementation-executor <plan-path>. Read that plan file, then launch the implementation-executor agent to work through it task by task.
Plan Structure
Implementation plans are TOML files following the compilable-plan-spec:
[meta]
title = "Phase X.Y: <Phase Name>"
source_branch = "branch-name"
created = "YYYY-MM-DD"
[dependencies]
# task_id = ["dep1", "dep2"] — omit if all tasks are independent
# TASK-3 = ["TASK-1", "TASK-2"] — TASK-3 depends on 1 and 2
[tasks.TASK-1]
description = "Task description"
type = "replace" # "replace" | "create" | "delete"
acceptance = [
"gfortran -c -Wall src/module.f90",
"make test",
]
[[tasks.TASK-1.changes]]
file = "path/to/file.f90"
before = '''
exact content to match
'''
after = '''
replacement content
'''
[tasks.TASK-2]
description = "Create new file"
type = "create"
acceptance = ["test -f path/to/new_module.f90"]
[[tasks.TASK-2.changes]]
file = "path/to/new_module.f90"
after = '''
file content here
'''
LSP-First Approach
Before making any code changes, leverage LSP tools for understanding and validation:
- Before editing: Use LSP to understand existing code structure, find subroutine/module definitions, check types
- During implementation: Use LSP diagnostics to catch errors early, before running gfortran
- For refactoring: Use LSP rename operations instead of manual find-replace
- For validation: Check LSP diagnostics first, then run acceptance commands
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.
- 5d ago First seen · 389 lines · 89 tokens per session scan A 142604913eb5
implementation-executor is a skill published in the GitHub repository TonyWu20/fortran-dev-pipeline (5 stars, last pushed 4mo ago), licensed MIT. It adds 89 tokens to every session and 4,966 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…
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…