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/sri-ln/rolecraft/agents-mdgit clone --depth 1 https://github.com/Sri-Ln/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/sri-ln/rolecraft/agents-md)<a href="https://agentmods.dev/instructions/sri-ln/rolecraft/agents-md"><img src="https://agentmods.dev/badge/instructions/sri-ln/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 | $0.01256 | $0.01256 |
| Opus 5 | $0.00628 | $0.00628 |
| Sonnet 5 | $0.00251 | $0.00251 |
| Haiku 4.5 | $0.00126 | $0.00126 |
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 3d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rolecraft — AI Agent Instructions
What rolecraft is
A JD-driven study companion. Paste a job description; rolecraft returns what to learn, what to build, and where else this kind of role exists. Designed for engineers who treat a job search as a study plan.
Outputs are learning artifacts — ranked concept lists, tech-stack study orders, niche project ideas, similar-role companies, a dashboard summarizing all of it. Not application volume. Not scores. Not PDFs to spam recruiters.
Voice and tone
Calm, study-coach-flavored. Brief, focused, declarative. Avoid hustle-mode phrasing ("AI-powered", "10x your job search", "automated outreach"). Project suggestions must be niche and business-aware — never generic CRUD demos. Every suggested project must explain the business problem it models alongside the tech.
Sources of truth
Every mode loads these (when they exist):
| File | Path | When loaded |
|---|---|---|
profile.yml |
user/profile/profile.yml |
ALWAYS — identity, target roles, industries, comp, location |
_profile.md |
user/profile/_profile.md |
ALWAYS — archetypes, adaptive framing, deal-breakers, energy/drain mapping |
cv.md |
user/profile/cv.md |
ALWAYS — canonical CV |
article-digest.md |
user/profile/article-digest.md |
ALWAYS if exists — proof points, STAR stories |
writing-samples/ |
user/profile/writing-samples/ |
When generating candidate-facing text |
| Mode-specific files | user/data/{file}.md |
When the mode reads/writes that file |
Never hardcode metrics or domain facts. Read them from the source-of-truth files at runtime.
Data contract (CRITICAL)
Two layers. Full breakdown in docs/DATA_CONTRACT.md.
User Layer (NEVER auto-updated; personalization goes HERE):
user/profile/*— identity, CV, framing, narrative, archetypes, deal-breakersuser/data/*— generated trackers, dashboard, reportsuser/profile/writing-samples/— optional tone samples; modes load only when generating candidate-facing text
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.
- 3d ago First seen · 95 lines · 1,256 tokens per session scan A 407dbc7ba8a2
rolecraft AGENTS.md is an instructions file published in the GitHub repository Sri-Ln/rolecraft (4 stars, last pushed 25d ago), licensed MIT. It adds 1,256 tokens to every session, about $0.0063 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 instructions, from other repositories
Resume-Builder CLAUDE.md
Instructions for jananthan30/Resume-Builder, covering resume builder - project context, quick start, option 1: claude code custom commands (recommended), resume only - dual optimized and cover letter only.
learn-faster-kit AGENTS.md
AGENTS.md instructions for hluaguo/learn-faster-kit, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
explain-this CLAUDE.md
Instructions for analyticalmonk/explain-this, covering claude.md, what this repo is, the three skills and how they relate, editing these skills and house constraints (the skills fail if these break).
ask-a-senior CLAUDE.md
Instructions for egorus1/ask-a-senior, covering ask-a-senior, the rule everything serves, layout, why there are hooks at all and conventions.
toefl-prep AGENTS.md
AGENTS.md instructions for epicsagas/toefl-prep, covering agents.md — toefl-prep plugin, 역할, 의존성 (사전 설치 필요), 학습 일정 (사용자 커스텀) and 스크립트/루브릭 경로.
rapid-domain-mastery copilot-instructions.md
Instructions for Emily2040/rapid-domain-mastery: This repository contains a portable agent skill called rapid-domain-mastery.