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/naifuliang/profilecraft-agent/agents-mdgit clone --depth 1 https://github.com/naifuliang/profilecraft-agentWhat 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 | $0.02069 | $0.02069 |
| Opus 5 | $0.01035 | $0.01035 |
| Sonnet 5 | $0.00414 | $0.00414 |
| Haiku 4.5 | $0.00207 | $0.00207 |
Grade A, and why
profilecraft-agent 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 2d 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file governs coding agents working anywhere in this repository. It is intentionally named AGENTS.md, the standard project-instruction filename recognized by Codex and other agent tooling.
Mission
Build a trustworthy, API-first toolkit that helps people improve their own professional presence and perform narrowly supported LinkedIn actions through official APIs.
The product must remain useful without becoming a scraper, browser bot, outreach bot, or engagement-manipulation tool.
Non-negotiable product boundaries
- Do not implement LinkedIn page scraping, DOM extraction, search-result harvesting, or crawling.
- Do not implement browser control, form automation, extension overlays, anti-detection behavior, CAPTCHA handling, or rate-limit evasion for LinkedIn.
- Do not implement automated connection requests, contact downloads, messages, InMail, follows, reactions, comments, or engagement loops.
- Do not accept or persist LinkedIn passwords, cookies, session tokens, or client secrets through prompts, CLI arguments, logs, fixtures, or source files.
- Do not call undocumented or reverse-engineered LinkedIn endpoints.
- Do not imply affiliation with or endorsement by LinkedIn.
- Do not add a live mutation without an official API route, an exact preview, explicit confirmation, a process-level write gate, and tests proving fail-closed behavior.
- Do not weaken these boundaries to make a demonstration pass. Offer a compliant alternative instead.
These are repository requirements, not optional style preferences.
Repository map
src/profile.ts: strict profile input schemas and audit result types.src/audit.ts: deterministic profile scoring. It must not call external services.src/policy.ts: centralized operation classification and product boundaries.src/posts.ts: post normalization, validation, previewing, and confirmation fingerprints.src/linkedin.ts: the only production module that sends LinkedIn HTTP requests.src/cli.ts: thin human-facing adapter over the core.src/mcp-server.ts: thin agent-facing adapter over the same core.src/mcp.ts: stdio entrypoint; never write diagnostics to stdout.skills/profilecraft: canonical portable skill.plugins/profilecraft-agent: Codex plugin with a synchronized copy of the skill.scripts: artifact and secret checks; keep them deterministic and offline.tests: unit and in-memory MCP integration tests. No test may contact LinkedIn.docs: architecture, threat model, and roadmap.
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.
- 2d ago First seen · 186 lines · 2,069 tokens per session scan A cf94df7cedb8
profilecraft-agent AGENTS.md is an instructions file published in the GitHub repository naifuliang/profilecraft-agent (0 stars, last pushed 4d ago), licensed MIT. It adds 2,069 tokens to every session, about $0.0103 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.