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 rodolfochicone/rc-project --skill rc-writing-for-agentsgit clone --depth 1 https://github.com/rodolfochicone/rc-projectWrote 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/rodolfochicone/rc-project/rc-writing-for-agents)<a href="https://agentmods.dev/skills/rodolfochicone/rc-project/rc-writing-for-agents"><img src="https://agentmods.dev/badge/skills/rodolfochicone/rc-project/rc-writing-for-agents/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/rodolfochicone/rc-project/rc-writing-for-agents"><img src="https://agentmods.dev/badge/skills/rodolfochicone/rc-project/rc-writing-for-agents.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 | $0.00038 | $0.02543 |
| Opus 5 | $0.00019 | $0.01272 |
| Sonnet 5 | $0.00008 | $0.00509 |
| Haiku 4.5 | $0.00004 | $0.00254 |
Grade A, and why
rc-writing-for-agents 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing for Agents
Every artifact an agent reads — a skill, a resident instruction file, a hook, a pointer doc — is the same object under different loading rules. They shared four skills and one doctrine; now they share one skill, because the doctrine is the part that matters and it was written four times.
The goal is predictability: the agent taking the same process every run, not producing the same output. Every lever below serves it.
Bold terms are defined in references/glossary.md.
Branches
| The artifact | Read |
|---|---|
| A skill — new, bloated, or with triggers that don't fire | references/authoring-procedure.md, then audit with references/checklist.md |
A skill whose references/ the agent ignores |
references/loading-diagnosis.md in full, before proposing a fix |
AGENTS.md / CLAUDE.md — resident context |
references/resident-files.md |
| A hook — a rule that must hold every time | references/hooks.md |
| "Where is my context window going?" | references/context-audit.md |
Every branch ends in a written audit, item by item — fix each Fail and re-audit. A document that reads well but fails its audit is not done. The doctrine below governs every line you write in any branch, not just the ones a procedure file mentions.
The two budgets
Every authoring decision trades these against each other:
- Context load — material present in the window regardless of use: a skill's
description, every line of a resident file, an MCP tool schema. Paid every turn, on every task, whether or not it applies. - Cognitive load — the human cost of knowing what exists and when to reach for it. A user-invoked skill has zero context load and spends this instead: you become the index.
Neither is free, so "just add it" is never the answer. A rule bearing on 5% of sessions taxes the other 95%, and rules dilute each other — instruction-following is a budget, so a bloated file enforces less, with the critical rule drowning in the noise.
What ships with it
10 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.
- assets/SKILL.template.md 1.5 KB
- references/authoring-procedure.md 4.4 KB
- references/checklist.md 5.0 KB
- references/context-audit.md 4.3 KB
- references/glossary.md 18 KB
- references/hook-events.md 2.9 KB
- references/hooks.md 4.4 KB
- references/loading-diagnosis.md 6.9 KB
- references/resident-files.md 5.4 KB
- scripts/validate-metadata.py 2.4 KB runs code
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 · 187 lines · 38 tokens per session scan A f73ed78dc9bf
rc-writing-for-agents is a skill published in the GitHub repository rodolfochicone/rc-project (19 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 2,543 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
mle-workflow
Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.
autonomous-loops
Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.
react-patterns
React 18/19 patterns including hooks discipline, server/client component boundaries, Suspense + error boundaries, form actions, data fetching, state management decision trees, and accessibility-first composition. Use when writing or reviewing React components.
content-engine
Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
agent-carnet
Use this skill when the user asks to save, recall, find, or organize notes. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check the notebook', 'find in carnet'. Also use proactively when discovering findings worth preserving across sessions.