writing-plan-docs

writing-plan-docs is a skill for Claude Code, Codex from permit0-ai/permit0. It costs 54 tokens per session (1,777 once invoked), scanned A, original, Apache-2.0.

A documentation workflow for planning new features, integrations, packs, crates, or major changes in the permit0 software repository. It organizes the plan into documents covering the goal, data flow, implementation, configuration, testing, and limits.

In plain words
What is it for?
Use it to write repository-specific feature plans, describe interfaces and data flow, document setup choices, and outline testing and limitations.
Why use it?
It turns a large or uncertain change into a clear written design that developers can review before coding.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/permit0-ai/permit0/writing-plan-docs
Any agent
npx skills add permit0-ai/permit0 --skill writing-plan-docs
Clone the repo
git clone --depth 1 https://github.com/permit0-ai/permit0

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for writing-plan-docs

README.md
[![agentmods](https://agentmods.dev/badge/skills/permit0-ai/permit0/writing-plan-docs.svg)](https://agentmods.dev/skills/permit0-ai/permit0/writing-plan-docs)
Your own site
<a href="https://agentmods.dev/skills/permit0-ai/permit0/writing-plan-docs"><img src="https://agentmods.dev/badge/skills/permit0-ai/permit0/writing-plan-docs.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,777 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00054 $0.01777
Opus 5 $0.00027 $0.00889
Sonnet 5 $0.00011 $0.00355
Haiku 4.5 $0.00005 $0.00178

Measured 5d ago against content hash cdd82da9ecb9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

writing-plan-docs 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 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.

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.

skills/writing-plan-docs/SKILL.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing Plan Docs for permit0

When to Use

Use this skill when the user asks you to plan a new integration (e.g. a new agent host like Codex, Cursor, CrewAI), a new pack, a new crate, or any multi-step change that benefits from upfront design before code.

Where to Place Plans

docs/plans/<feature-name>/
  00-overview.md
  01-protocol.md          (if wire format / API contract exists)
  02-implementation.md
  03-configuration.md     (if user-facing setup is needed)
  04-testing.md
  05-limitations.md
  • Path: Always under docs/plans/<feature-name>/.
  • Numbering: Prefix with 00- through 0N- for reading order.
  • Naming: Use lowercase-kebab-case for the feature directory.

Documents to Write

Not every plan needs all six docs. Pick the ones that apply.

00-overview.md (always required)

The entry point. A reader should understand what, why, and how far after reading only this file.

Cover:

  1. Goal -- What this feature does, in one paragraph. If it replicates an existing integration, say so and link to the reference implementation.
  2. Data flow -- ASCII or mermaid diagram showing the end-to-end path.
  3. Comparison table -- If a similar feature exists (e.g. Claude Code integration), a side-by-side table of what is the same and what differs.
  4. Scope -- Bullet list of what is in v1 vs deferred to v2+.
  5. Crate dependencies -- Which crates are touched and which are not. permit0's architecture makes most features crate-local; call that out.

Header template:

# 00 -- <Feature>: Overview and Architecture

**Status:** Draft
**Depends on:** None
**Blocks:** 01-protocol, 02-implementation

01-protocol.md (when there is a wire format)

Exact schemas for any JSON, TOML, HTTP, or stdin/stdout contract.

Cover:

  1. Input schema -- Every field, type, whether always present or optional.
  2. Output schema -- Every possible response shape. Show concrete JSON examples for each verdict/outcome.
  3. Mapping table -- How permit0 types (Permission, Tier, etc.) map to the external system's values.
  4. Error handling matrix -- What happens on crash, timeout, malformed output, transport failure. Table format works well.
  5. Session / identity extraction -- Where session IDs come from, fallback chain.
  6. Future extensions -- Schemas or hooks that exist in the external system but are not used in v1.

Read the full file on GitHub · 201 lines

Changes

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.

  1. 5d ago First seen · 201 lines · 54 tokens per session scan A cdd82da9ecb9

Subscribe to this mod's changes

writing-plan-docs is a skill published in the GitHub repository permit0-ai/permit0 (185 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 54 tokens to every session and 1,777 once invoked, about $0.0003 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.