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/yrangana/plans/claude-mdgit clone --depth 1 https://github.com/yrangana/PlansWrote 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/yrangana/plans/claude-md)<a href="https://agentmods.dev/instructions/yrangana/plans/claude-md"><img src="https://agentmods.dev/badge/instructions/yrangana/plans/claude-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 | $0.02397 | $0.02397 |
| Opus 5 | $0.01198 | $0.01198 |
| Sonnet 5 | $0.00479 | $0.00479 |
| Haiku 4.5 | $0.00240 | $0.00240 |
Grade C, and why
Plans CLAUDE.md scanned grade C with 1 finding 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 5d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf /tmp/test-plans && mkdir /tmp/test-plans How it starts
The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md, plans repo
This file is for AI assistants (Claude Code, Antigravity, Cursor) and human contributors working on the plans repo itself, not for projects that adopt the system.
Maintainers may keep additional personal context in a CLAUDE.local.md next to this file. That file is gitignored and overrides nothing here, it just adds local conveniences (paths, preferences) on top.
What this repo is
A shareable spec-driven planning convention. The repo contains:
- Documentation explaining the system (
README.md,docs/) - A drop-in template users copy into their own projects, bundled inside the skill (
template/skills/plans/template/plans/) - A bootstrap script that automates the copy (
scripts/init.sh) - A Claude Code plugin (
.claude-plugin/) that delivers the/plansskill as the primary adoption path; the scripts remain the fallback for other assistants - A static site rendered by GitHub Pages from
web/(landing page, live roadmap demo, status demo, slides, docs) - Static assets used by the README (
examples/demo.svg, screenshots)
This repo does not itself adopt the planning convention by default. It's the system, not a user of the system. (See "Using the system on this repo" below if you change your mind.)
Repo structure
plans/
├── README.md # Top-level pitch + quick start
├── LICENSE # MIT
├── CLAUDE.md # This file
├── docs/ # Standalone guide for adopters
│ ├── reference.md # Full technical spec
│ ├── blog-post.md # Narrative explanation
│ └── presentation.html # Slideshow
├── template/ # What users copy into their projects
│ └── skills/
│ └── plans/ # The /plans skill (self-sufficient package)
│ ├── SKILL.md
│ ├── references/ # Per-mode logic loaded on demand
│ └── template/ # Bundled project template
│ ├── CLAUDE.md.snippet # Section adopters paste into their CLAUDE.md (skills/plans/template)
│ └── plans/ # The directory adopters drop into their repo
│ ├── README.md # Onboarding for adopters
│ ├── STATUS.md # Empty front-door template
│ ├── plans.json # Empty starter ({ project, plans } shape; see docs/reference.md)
│ ├── roadmap.html # Interactive dashboard
│ ├── active/ # With EXAMPLE_PLAN.md showing the format
│ ├── shipped/
│ └── superseded/
├── scripts/
│ ├── init.sh # Bootstraps plans/ and installs skill in a target project
│ └── update.sh # Updates system files (roadmap.html, README.md, skill)
├── .claude-plugin/ # Claude Code plugin manifest, delivers /plans as the primary path
├── web/ # GitHub Pages site (deployed by .github/workflows)
│ ├── index.html # Landing page
│ ├── roadmap.html # Live roadmap demo (inline data)
│ ├── status.html # Live STATUS.md demo
│ ├── presentation.html # Slides
│ └── docs.html # Browsable docs
└── examples/ # Static assets for the README
├── demo.svg # Animated terminal demo
├── screenshot-dashboard.png
└── screenshot-status.png
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.
- 5d ago First seen · 192 lines · 2,397 tokens per session scan C 88df1ed4a912
Plans CLAUDE.md is an instructions file published in the GitHub repository yrangana/Plans (2 stars, last pushed 1mo ago), licensed MIT. It adds 2,397 tokens to every session, about $0.0120 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
spec-superflow GEMINI.md
Gemini CLI instructions for MageByte-Zero/spec-superflow, covering spec-superflow and spec-superflow v1.2.0 | 阶段: {{state}} | 工作流: {{workflow}}.
spec-superflow copilot-instructions.md
Copilot instructions for MageByte-Zero/spec-superflow, covering phase guard, ✅ 允许操作, ⛔ 禁止操作 and 🔔 决策点.
specmanager CLAUDE.md
Instructions for joanseg/specmanager, covering claude.md, what this repo is, layout, architecture (the big picture) and lifecycle gate quirks worth memorising.
pilot-shell CLAUDE.md
Claude Code instructions for maxritter/pilot-shell, a project described as: Professional context and harness engineering for Claude Code and OpenAI Codex. Build production-grade software with spec-driven development, TDD, persistent memory, quality gates, code intelligence, human oversight, and end-to-end verification.
spec-manager CLAUDE.md
Instructions for loki-ai-ch/spec-manager, covering claude.md, spec-driven development — no vibe coding, build & test commands, architecture and source layout.
spec-manager AGENTS.md
Instructions for loki-ai-ch/spec-manager, covering spec-manager workflow capsule, mandatory workflow and common commands.