A documentation workflow for maintaining Perigon's bilingual, versioned documentation. It covers English and Chinese pages and tracks changes from related command-line, template, and module projects.

Use it to find affected documentation, compare related workspace changes, update matching English and Chinese pages, and decide when a new page is needed.

It helps keep documentation aligned with actual software changes and avoids creating duplicate pages when an existing page should be corrected.

docs — Skill for Claude Code and Codex by AterDev/Perigon.CLI

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.

Any agent

npx skills add AterDev/Perigon.CLI --skill docs

Clone the repo

git clone --depth 1 https://github.com/AterDev/Perigon.CLI

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/aterdev/perigon.cli/docs/github.svg)](https://agentmods.dev/skills/aterdev/perigon.cli/docs)

Your own site

<a href="https://agentmods.dev/skills/aterdev/perigon.cli/docs"><img src="https://agentmods.dev/badge/skills/aterdev/perigon.cli/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/aterdev/perigon.cli/docs"><img src="https://agentmods.dev/badge/skills/aterdev/perigon.cli/docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 644 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00067	$0.00644
Opus 5.5	$0.00027	$0.00258
Sonnet 5.5	$0.00013	$0.00129
Haiku 4.5	$0.00007	$0.00064

Measured 1mo ago against content hash 898f265cf836, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 1mo 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.

.agents/skills/docs/SKILL.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Perigon Documentation Workflow

Workspace Scope

The authoritative documentation lives under Perigon.docs/Content/docs/Perigon.
Documentation is versioned by folder, then split by language: zh-CN/<version> and en-US/<version>.
Source changes that drive Perigon docs usually come from Perigon.CLI, Perigon.template, and Perigon.Modules.

Workflow

Identify the affected feature, command, template behavior, module behavior, or contributor workflow.
Check workspace changes in Perigon.template, Perigon.CLI, and Perigon.Modules first to determine what actually changed.
Ignore unrelated diffs and extract only Perigon-relevant behavior, constraints, commands, paths, version notes, or user-visible workflow changes.
Search existing pages under Perigon.docs/Content/docs/Perigon for the closest matching topic before creating new content.
Prefer updating or correcting an existing document when the topic already exists.
Create a new page only when the change introduces a clearly new concept, workflow, or reference topic.
Keep Chinese and English docs aligned in structure and meaning. When one side changes, update the matching page in the other language unless the user explicitly asks for one language only.
Place content in the correct version folder. If behavior differs by version, document the version-specific scope explicitly instead of silently overwriting another version's guidance.

Conventions

Preserve the existing section taxonomy and naming style under both zh-CN and en-US.
Keep folder symmetry when equivalent pages exist in both languages.
Document observable behavior from the repositories, not speculation or roadmap assumptions.
Prefer concise task-oriented guidance, with commands, paths, prerequisites, and limitations called out directly.
When adding a new page in a section that uses .order, update the corresponding .order file so navigation stays correct.
If the source change is internal only and has no user, contributor, or operator impact, do not add noise to the docs.

Read the full file on GitHub · 45 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.

1mo ago First seen · 45 lines · 67 tokens per session scan A 898f265cf836

Subscribe to this mod's changes

docs is a skill published in the GitHub repository AterDev/Perigon.CLI (54 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 67 tokens to every session and 644 once invoked, about $0.0003 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.

Code Generation Localization Writing and docs asp-net-core cli copilot dotnet dto-generator

skillit-docs

Documentation conventions for generating high-quality AI agent skills from TypeScript source. Use when preparing a library for skill generation, auditing JSDoc quality, fixing audit warnings, writing @useWhen/@avoidWhen/@never tags, or asking about documentation conventions for skills. Use this even if the user just…

pradeepmouli/skillit · 85 tokens

skillit-bootstrap

Bootstrap an AI-agent skill from a TypeScript codebase by running the deterministic skillit generate/audit loop and enriching repo source (JSDoc, README, config-type properties, MCP tool annotations, examples, package.json) until the skill reaches its grade target. Use for cli, typedoc, config, or mcp (build-mode)…

pradeepmouli/skillit · 84 tokens

docs