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 felipepg22/FPGSkills --skill fpg-agents-md-writergit clone --depth 1 https://github.com/felipepg22/FPGSkillsWrote 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/felipepg22/fpgskills/fpg-agents-md-writer)<a href="https://agentmods.dev/skills/felipepg22/fpgskills/fpg-agents-md-writer"><img src="https://agentmods.dev/badge/skills/felipepg22/fpgskills/fpg-agents-md-writer/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/felipepg22/fpgskills/fpg-agents-md-writer"><img src="https://agentmods.dev/badge/skills/felipepg22/fpgskills/fpg-agents-md-writer.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 | $0.00069 | $0.00694 |
| Opus 5 | $0.00034 | $0.00347 |
| Sonnet 5 | $0.00014 | $0.00139 |
| Haiku 4.5 | $0.00007 | $0.00069 |
Grade A, and why
fpg-agents-md-writer 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FPG AGENTS.md Writer
Build concise, evidence-backed instruction systems for coding agents. Treat every
AGENTS.md as a task router, not a repository encyclopedia.
Select the outcome
Infer one of these outcomes from the request:
- Audit: Research and report issues. Do not propose or write files unless asked.
- Proposal: Research and present a file plan. Do not write files.
- Write: Research, present the proposal, wait for approval, then implement it.
When asked to create, update, improve, or reorganize instructions, use the Write outcome. Never skip its approval gate, even when the initial request says to write.
Execute the workflow
- Read references/research.md completely and research the repository without changing it.
- Read references/proposal.md completely and present one compact proposal with recommended choices.
- Stop and wait for explicit approval in Write mode. Apply requested corrections and ask again when they materially change the proposal.
- After approval, read references/authoring.md completely and create or update only the approved files.
- Before finishing, read references/validation.md completely and perform its checks.
Enforce non-negotiable rules
- Keep every new or rewritten root or nested
AGENTS.mdat 100 physical lines or fewer. Count internally; do not report routine line counts. - If an existing
AGENTS.mdexceeds 100 lines, propose a compliant refactor and wait. Leave it untouched when the user declines. - Choose supporting guideline subjects and locations from repository evidence.
Reuse an established documentation convention; otherwise default to
.agents/guidelines/. - Let a guideline exceed 100 lines when one coherent subject requires it. Split by responsibility or task-routing need, never by length alone.
- Put repository-wide rules, essential commands, critical prohibitions, and
task-based routes in
AGENTS.md. Put explanations, examples, and specialized knowledge in guidelines. - Preserve valid existing guidance. Never replace an instruction system wholesale without explicit approval.
- Ask before every destructive operation, including deleting, renaming, merging, or replacing existing files. General approval to update instructions is not approval for an unlisted destructive action.
- Write platform-neutral, imperative guidance. Add host-specific instructions only when repository evidence or the user requires them.
- Do not invent commands, architecture, conventions, or policy. Stop and ask when evidence is sparse or contradictory.
- Do not add scripts or executables to a target repository for validation.
What ships with it
7 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.
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 · 66 lines · 69 tokens per session scan A 570ea14317ba
fpg-agents-md-writer is a skill published in the GitHub repository felipepg22/FPGSkills (11 stars, last pushed 5d ago), licensed MIT. It adds 69 tokens to every session and 694 once invoked, about $0.0003 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…