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 instructions/rolecraft-sh/rolecraft/agents-mdgit clone --depth 1 https://github.com/rolecraft-sh/rolecraftWrote 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/instructions/rolecraft-sh/rolecraft/agents-md)<a href="https://agentmods.dev/instructions/rolecraft-sh/rolecraft/agents-md"><img src="https://agentmods.dev/badge/instructions/rolecraft-sh/rolecraft/agents-md.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 | $0.00845 | $0.00845 |
| Opus 5 | $0.00423 | $0.00423 |
| Sonnet 5 | $0.00169 | $0.00169 |
| Haiku 4.5 | $0.00085 | $0.00085 |
Grade A, and why
rolecraft AGENTS.md 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 4d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rolecraft — Development Guidelines
📖 Agent discovery paths are in
docs/agents.md
⚠️ STARTUP CHECKLIST (read before every task)
git checkout main && git pull— start from latest maingit checkout -b feat/my-featureorfix/my-bug— create branch- Do all work on the feature branch (never on main)
npm run lint— check syntax before pushingnpm test— run tests- Never leave changes that break tests
- Write tests for new features
- Update docs (README, docs/) when needed
- Test
--dry-runflag if the feature supports it git add ... && git commit -m "type: short description"— title only, no bodygit push -u origin <branch>— pushgh pr create— open PR with short one-sentence body- Before merging, wait for all GitHub Actions checks to pass (
gh run watchor check PR status). Never merge while checks are running.
Workflow
- Before starting any task, ensure you're on
mainwith latest changes (git checkout main && git pull), then create a new branch specific to the task (git checkout -b feat/my-featureorfix/my-bug) - Complete all work on the feature branch
- After completing the work, run
npm run lintand the tests:node --test --test-concurrency=1 - Never leave changes that break tests
- Write tests for new features
- Update documentation (README, docs/) when needed
- Test the
--dry-runflag if the feature supports it - After tests pass, commit the changes (title only, no body), push the branch, and open a PR (one-sentence body)
- Before merging, wait for all GitHub Actions checks to pass (
gh run watchor check PR status). Never merge while checks are running.
Interaction rules
- Chat vs dev mode: Before writing any code, confirm whether the user wants development or just information. Ask: "Are you asking me to develop something or just asking for information?"
- Commit messages: Title only, no body. Example:
feat: add rolecraft mcp check command - PR body: One-sentence summary. Example: "Adds rolecraft mcp check command for npm update checks."
- Branch strategy: Always branch from latest main for any work that requires a commit, unless the user explicitly says otherwise.
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.
- 4d ago First seen · 54 lines · 845 tokens per session scan A 5ac9595e7802
rolecraft AGENTS.md is an instructions file published in the GitHub repository rolecraft-sh/rolecraft (75 stars, last pushed 7d ago), licensed MIT. It adds 845 tokens to every session, about $0.0042 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 instructions, from other repositories
agent-handoff AGENTS.md
Instructions for xiaomaimuchanyiyiba/agent-handoff, covering project context, purpose, structure and conventions.
webflow-skills CLAUDE.md
Claude Code instructions for webflow/webflow-skills, covering project overview, repository structure, ci validation, what ci checks and 2. marketplace and plugin configs exist.
MathModelAgent CLAUDE.md
Claude Code instructions for jihe520/MathModelAgent, covering claude.md, 项目概述, commands, 后端 and 安装依赖.
lime AGENTS.md
AGENTS.md instructions for limecloud/lime, covering lime 源码仓库指南, 事实源, 工程约束, 协议与质量 and 执行方式.
clean-code-skills clean-code.instructions.md
Instructions for btseee/clean-code-skills, covering clean-code instructions, clean code rules (clean-code-skills), work loop, dependency direction and file and code placement.
skills AGENTS.md
AGENTS.md instructions for PsiACE/skills, covering navigation notes and conventions.