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 skills add permit0-ai/permit0 --skill writing-plan-docsgit clone --depth 1 https://github.com/permit0-ai/permit0Wrote 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/skills/permit0-ai/permit0/writing-plan-docs)<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/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00054 | $0.01777 |
| Opus 5.5 | $0.00022 | $0.00711 |
| Sonnet 5.5 | $0.00011 | $0.00355 |
| Haiku 4.5 | $0.00005 | $0.00178 |
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 2mo 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 — 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-through0N-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:
- Goal -- What this feature does, in one paragraph. If it replicates an existing integration, say so and link to the reference implementation.
- Data flow -- ASCII or mermaid diagram showing the end-to-end path.
- 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.
- Scope -- Bullet list of what is in v1 vs deferred to v2+.
- 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:
- Input schema -- Every field, type, whether always present or optional.
- Output schema -- Every possible response shape. Show concrete JSON examples for each verdict/outcome.
- Mapping table -- How permit0 types (
Permission,Tier, etc.) map to the external system's values. - Error handling matrix -- What happens on crash, timeout, malformed output, transport failure. Table format works well.
- Session / identity extraction -- Where session IDs come from, fallback chain.
- Future extensions -- Schemas or hooks that exist in the external system but are not used in v1.
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.
- 2mo ago First seen · 201 lines · 54 tokens per session scan A cdd82da9ecb9
writing-plan-docs is a skill published in the GitHub repository permit0-ai/permit0 (192 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 54 tokens to every session and 1,777 once invoked, about $0.0002 per session on Opus 5.5. 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.
writing-plan-docs compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| writing-plan-docspermit0-ai/permit0 | Skill | 192 | 4mo ago | Apache-2.0 | A | 54 | Claude Code, Codex |
| interpret-resultsairblackbox/airblackbox | Skill | 25 | 4d ago | Apache-2.0 | A | 49 | Claude Code |
| compliance-scanairblackbox/airblackbox | Skill | 25 | 4d ago | Apache-2.0 | A | 51 | Claude Code |
| deep-code-reviewPeaky8linders/eu-ai-act-scanner | Skill | 6 | 4d ago | Apache-2.0 | A | 34 | Claude Code, Codex |
| Agent Audit Traillxyeternal/MalSkillBench | Skill | 64 | 4d ago | none | A | 59 | Claude Code, Codex |
| governancedingdawg/dingdawg-governance | Skill | 1 | 3mo ago | MIT | A | 13 | Claude Code |
| governancedingdawg/dingdawg-governance | Skill | 1 | 3mo ago | MIT | A | 13 | Claude Code, Codex |