docs

A documentation workflow that creates or updates project guides by examining the actual code. It can cover APIs, services, architecture, business concepts, operations, or getting started instructions.

In plain words
What is it for?
Use it after code or infrastructure changes to refresh API references, service docs, architecture notes, domain models, runbooks, quickstarts, or all outdated documentation.
Why use it?
It reduces stale or invented documentation by basing each statement on code that was inspected.

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/makigjuro/cloudstack-ai-plugins/docs
Any agent
npx skills add makigjuro/cloudstack-ai-plugins --skill docs
Clone the repo
git clone --depth 1 https://github.com/makigjuro/cloudstack-ai-plugins

Made for: Claude Code, Codex.

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,327 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 $0.00043 $0.02327
Opus 5 $0.00022 $0.01163
Sonnet 5 $0.00009 $0.00465
Haiku 4.5 $0.00004 $0.00233

Measured yesterday against content hash c76bd58b4fb3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 yesterday.

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.

plugins/dev-workflow/skills/docs/SKILL.md · 281 lines

How it starts

The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generate / Update Documentation

Generate or update markdown documentation by analyzing the actual codebase. Never fabricate -- every statement must be backed by code you've read.

Arguments

  • {target} -- What to document. One of:
    • service {name} -- Full service documentation (endpoints, events, config)
    • api {service} -- API endpoint reference for a service
    • architecture -- Update the technical architecture doc
    • domain -- Update the domain model doc
    • runbook {service} -- Operational runbook (health checks, alerts, troubleshooting)
    • quickstart -- Update the quickstart / getting started guide
    • all -- Regenerate all outdated docs

If no argument given, detect what's changed since last docs update and suggest what needs refreshing.

Configuration

Read cloudstack.json from the project root at the start of execution. Extract:

  • NAMESPACE = project.namespace
  • SOLUTION = backend.solutionPath
  • SERVICES = backend.services[]
  • FRONTEND_PATH = frontend.path (default: web)
  • CHARTS_PATH = infrastructure.chartsPath (default: deploy/charts)
  • TERRAFORM_PATH = infrastructure.terraformPath

If cloudstack.json does not exist, auto-detect by scanning the project structure.

Process

Step 1: Detect Scope

If no target specified:

# Find docs that may be stale -- compare last doc commit vs last code commit
git log -1 --format=%H -- docs/
git log -1 --format=%H -- src/ ${FRONTEND_PATH} ${CHARTS_PATH} ${TERRAFORM_PATH}

# Show what code changed since docs were last updated
git diff {last-docs-commit}..HEAD --stat -- src/ ${FRONTEND_PATH} ${CHARTS_PATH} ${TERRAFORM_PATH}

Present the user with a summary of what's changed and recommend which docs to update.

Step 2: Gather Evidence

Read the actual code -- do NOT guess or use stale memory. For each doc type:

Service doc (docs/services/{service-name}/README.md):

  1. Read src/{Service}/{Service}.Host/Program.cs -- DI, middleware, config sections
  2. Read src/{Service}/{Service}.Host/Endpoints/ -- all endpoint files
  3. Read src/{Service}/{Service}.Application/Commands/ -- all command records
  4. Read src/{Service}/{Service}.Application/Queries/ -- all query records
  5. Read src/{Service}/{Service}.Infrastructure/DependencyInjection.cs -- external dependencies
  6. Read src/{Service}/{Service}.Infrastructure/Persistence/Configurations/ -- DB schema
  7. Grep for messaging subjects/topics in the service
  8. Read Helm chart values if present: ${CHARTS_PATH}/{service-name}/values.yaml
  9. Read appsettings.json in the Host project -- configuration keys

Read the full file on GitHub · 281 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. yesterday First seen · 281 lines · 43 tokens per session scan A c76bd58b4fb3

Subscribe to this mod's changes

docs is a skill published in the GitHub repository makigjuro/cloudstack-ai-plugins (1 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 2,327 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories