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/shiquda/roadmap-skill/agents-mdgit clone --depth 1 https://github.com/shiquda/roadmap-skillWhat 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 | $0.01828 | $0.01828 |
| Opus 5 | $0.00914 | $0.00914 |
| Sonnet 5 | $0.00366 | $0.00366 |
| Haiku 4.5 | $0.00183 | $0.00183 |
Grade A, and why
roadmap-skill 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 — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Guidelines
Git Commit Messages
All commit messages must be written in English.
Format
Follow Conventional Commits specification:
<type>[optional scope]: <description>
[optional body]
[optional footer(s)]
Types
feat: A new featurefix: A bug fixdocs: Documentation only changesstyle: Changes that do not affect the meaning of the code (white-space, formatting, etc)refactor: A code change that neither fixes a bug nor adds a featureperf: A code change that improves performancetest: Adding missing tests or correcting existing testschore: Changes to the build process or auxiliary tools
Examples
feat: add task priority sorting to kanban board
fix: resolve CI build failure by switching from Taobao registry to npm official registry
docs: update README with installation instructions
refactor(storage): simplify task update logic
Build & Test Commands
# Development
npm run dev # Start development mode with watch
# Building
npm run build # Full build (Node + Web)
npm run build:web # Build only web frontend
# Type checking
npm run typecheck # Run TypeScript type checking without emitting
# Testing
npm run test # Run tests in watch mode
npm run test:unit # Run unit tests once
npm run test:integration # Run integration tests once
# Run a single test file
npx vitest run tests/unit/storage.test.ts
# Run tests matching a pattern
npx vitest run --reporter=verbose --testNamePattern="createProject"
Code Style Guidelines
TypeScript
- Target: ES2022 with NodeNext module resolution
- Strict mode: Enabled - all strict TypeScript options must pass
- Unused code: Not allowed (noUnusedLocals, noUnusedParameters)
- Implicit returns: Not allowed (noImplicitReturns)
Imports & Modules
- Use ES modules (
"type": "module"in package.json) - Include
.jsextension in imports:import { foo } from './bar.js' - Prefer named imports over default imports
- Group imports: built-ins → external → internal (separated by blank line)
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 · 282 lines · 1,828 tokens per session scan A 793690cdeb53
roadmap-skill AGENTS.md is an instructions file published in the GitHub repository shiquda/roadmap-skill (77 stars, last pushed 5mo ago), licensed MIT. It adds 1,828 tokens to every session, about $0.0091 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
kaneo AGENTS.md
AGENTS.md instructions for usekaneo/kaneo, covering kaneo agent guide, principles, architecture, boundaries that must hold and follow a change through.
kaneo CLAUDE.md
Claude Code instructions for usekaneo/kaneo, a project described as: 🎯 All you need. Nothing you don't. Open source project management that works for you, not against you.
FlowBoard AGENTS.md
Instructions for rasimme/FlowBoard, covering flowboard — agent entry point, start here and where things live.
pm-manager AGENTS.md
Instructions for wei63w/pm-manager: 可安装的 Agent Skill 位于 skills/pm-manager/。.
jjj CLAUDE.md
Instructions for doug/jjj, covering claude.md, project overview, build commands, rust cli and vs code extension.
jjj AGENTS.md
Instructions for doug/jjj, covering agent instructions, before you write anything, read this first, house rules and verifying changes to this repository.