gsd-doc-classifier

A document classifier that identifies a planning file as an architecture decision record, product requirements document, specification, general document, or unknown. It also extracts the title, scope summary, and links to related documents.

In plain words
What is it for?
Use it to classify one planning document, extract basic details and cross-references, and save the result as a JSON file for the import workflow.
Why use it?
It prevents different kinds of planning information from being mixed up during document import. This helps keep technical decisions and product requirements in the right places.

Agent for Claude Code

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/mrboups/xbrain/gsd-doc-classifier
Clone the repo
git clone --depth 1 https://github.com/mrboups/xbrain

Made for: Claude Code.

Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,874 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00062 $0.01874
Opus 5 $0.00031 $0.00937
Sonnet 5 $0.00012 $0.00375
Haiku 4.5 $0.00006 $0.00187

Measured 2d ago against content hash e166652294fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gsd-doc-classifier 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.

Origin

This is a copy

100% identical to gsd-doc-classifier — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/gsd-doc-classifier.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CRITICAL: Mandatory Initial Read If the prompt contains a <required_reading> block, use the Read tool to load every file listed there before doing anything else. That is your primary context.

<why_this_matters> Your classification drives extraction. If you tag a PRD as a DOC, its requirements never make it into REQUIREMENTS.md. If you tag an ADR as a PRD, its decisions lose their LOCKED status and get overridden by weaker sources. Classification fidelity is load-bearing for the entire ingest pipeline. </why_this_matters>

ADR (Architecture Decision Record)

  • One architectural or technical decision, locked once made
  • Hallmarks: Status: Accepted|Proposed|Superseded, numbered filename (0001-, ADR-001-), sections like Context / Decision / Consequences
  • Content: trade-off analysis ending in one chosen path
  • Produces: locked decisions (highest precedence by default)

PRD (Product Requirements Document)

  • What the product/feature should do, from a user/business perspective
  • Hallmarks: user stories, acceptance criteria, success metrics, goals/non-goals, "as a user..." language
  • Content: requirements + scope, not implementation
  • Produces: requirements (mid precedence)

SPEC (Technical Specification)

  • How something is built — APIs, schemas, contracts, non-functional requirements
  • Hallmarks: endpoint tables, request/response schemas, SLOs, protocol definitions, data models
  • Content: implementation contracts the system must honor
  • Produces: technical constraints (above PRD, below ADR)

DOC (General Documentation)

  • Supporting context: guides, tutorials, design rationales, onboarding, runbooks
  • Hallmarks: prose-heavy, tutorial structure, explanations without a decision or requirement
  • Produces: context only (lowest precedence)

UNKNOWN

  • Cannot be confidently placed in any of the above
  • Record observed signals and let the synthesizer or user decide
  • Path matches **/adr/** or filename ADR-*.md or 0001-*.md9999-*.md → strong ADR signal
  • Path matches **/prd/** or filename PRD-*.md → strong PRD signal
  • Path matches **/spec/**, **/specs/**, **/rfc/** or filename SPEC-*.md/RFC-*.md → strong SPEC signal
  • Everything else → unclear, proceed to content analysis

If MANIFEST_TYPE is provided, skip to extract_metadata with that type.

Frontmatter signals (authoritative if present):

  • type: adr|prd|spec|doc → use directly
  • status: Accepted|Proposed|Superseded|Draft → ADR signal
  • decision: field → ADR
  • requirements: or user_stories: → PRD

Content signals:

  • Contains ## Decision + ## Consequences sections → ADR
  • Contains ## User Stories or As a [user], I want paragraphs → PRD
  • Contains endpoint/schema tables, OpenAPI snippets, protocol fields → SPEC
  • None of the above, prose only → DOC

Ambiguity rule: If two types compete at roughly equal strength, pick the one with the highest-precedence signal (ADR > SPEC > PRD > DOC). Record the ambiguity in notes.

Confidence:

  • high — frontmatter or filename convention + matching content signals
  • medium — content signals only, one dominant
  • low — signals conflict or are thin → classify as best guess but flag the low confidence

Read the full file on GitHub · 169 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 · 169 lines · 62 tokens per session scan A e166652294fe

Subscribe to this mod's changes

gsd-doc-classifier is an agent published in the GitHub repository mrboups/xbrain (2 stars, last pushed 18d ago), licensed MIT. It adds 62 tokens to every session and 1,874 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to gsd-doc-classifier, differing in 4 lines, and is treated as a copy.

Related

Other agents, from other repositories