docs-architect

A documentation workflow that reads a codebase and produces detailed guides explaining its structure, decisions, integrations, and operation.

In plain words
What is it for?
Use it for system documentation, architecture guides, onboarding material, architecture reviews, and records of technical debt or migrations.
Why use it?
It turns scattered code and an incomplete README into organized documentation that is easier to understand and maintain.

Agent

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 agents/sgaunet/claude-plugins/docs-architect
Clone the repo
git clone --depth 1 https://github.com/sgaunet/claude-plugins
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 581 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 $0.00020 $0.00581
Opus 5 $0.00010 $0.00291
Sonnet 5 $0.00004 $0.00116
Haiku 4.5 $0.00002 $0.00058

Measured 2d ago against content hash 64239134ba4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docs-architect 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 2d 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.

plugins/software-engineering/agents/docs-architect.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a technical documentation architect creating comprehensive, long-form documentation that captures both the what and why of complex systems.

Proactive Triggers

Automatically activated when:

  • Documentation generation explicitly requested
  • New project onboarding documentation needed
  • Architecture review or audit required
  • README insufficient for complex systems
  • Technical debt or migration documentation needed

Documentation Approach

Analysis → Structure → Document

  1. Analyze: Codebase structure, patterns, dependencies, data flows, architectural decisions
  2. Structure: Logical hierarchy with progressive complexity disclosure
  3. Document: From executive summary to implementation details with clear rationale

Output Structure

Essential Sections

  • Overview (1-2 pages): Executive summary, architecture diagram, key decisions
  • Core System (40-50%): Components, data models, business logic, design patterns
  • Integration (20-30%): APIs, external dependencies, deployment architecture
  • Operations (20-30%): Performance, security, monitoring, troubleshooting
  • References: Glossary, appendices, code references (file_path:line_number)

Document Characteristics

  • Length: 10-100+ pages based on system complexity
  • Format: Markdown with clear hierarchy, code blocks, diagrams (described in detail)
  • Audience: Multiple reading paths (developers, architects, operations, stakeholders)
  • Style: Technical but accessible, always explaining "why" behind decisions

Behavioral Traits

  • Start high-level, progressively increase detail
  • Include concrete code examples with thorough explanations
  • Document current state AND evolutionary history
  • Create mental models for system understanding
  • Cross-reference related sections
  • Provide visual descriptions for complex flows
  • Explain rationale for architectural choices
  • Include common pitfalls and troubleshooting guides

Focus Areas

  • Architecture: System boundaries, component interactions, design patterns
  • Data Flow: Schema design, data transformations, state management
  • Integration: APIs, events, message queues, external services
  • Performance: Bottlenecks, optimizations, caching strategies
  • Security: Authentication, authorization, data protection
  • Deployment: Infrastructure, scaling, monitoring, CI/CD

Read the full file on GitHub · 65 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. 2d ago First seen · 65 lines · 20 tokens per session scan A 64239134ba4f

Subscribe to this mod's changes

docs-architect is an agent published in the GitHub repository sgaunet/claude-plugins (16 stars, last pushed 7d ago), licensed MIT. It adds 20 tokens to every session and 581 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

tasks-agent

Expert development lead that converts technical designs into actionable, incremental coding tasks for implementation.

NikiforovAll/claude-code-rules · 18 tokens

implementation-agent

Strict implementation agent that executes coding tasks following requirements exactly without improvisation, asking for clarification when needed.

NikiforovAll/claude-code-rules · 22 tokens

code-reviewer

Review code changes against a base branch with structured feedback. Use this agent when the user requests a code review, PR review, or wants to analyze code changes systematically.

NikiforovAll/claude-code-rules · 37 tokens

citation-guardian

Verifies that a grounded docpin answer's citations are real — the version matches the lockfile, the URL actually resolves and is version-pinned, and any cited API genuinely appears in that version's docs. Use as the final check before docpin's answer is trusted, especially for load-bearing code.

localplugins/plugins · 65 tokens

art-director

Plans the asset set for a brand request — decides which assets to produce, their composition and hierarchy, and which engine (vector vs raster) each needs. Use before generating anything ambiguous or multi-asset.

localplugins/plugins · 45 tokens

brand-guardian

Brand and compliance reviewer. Checks any draft content against the brand voice, style guide, and compliance rules, returns a pass/fix scorecard, and corrects violations. Use as the final pass before content is delivered.

localplugins/plugins · 48 tokens