What is gsd-doc-classifier?

A planning-document classification agent that labels one document as an ADR, PRD, SPEC, DOC, or UNKNOWN and extracts its title, scope, and references. An ADR records a technical decision, while a PRD describes product requirements.

It helps process documents during project planning by identifying their type, summarizing their scope, and recording cross-references in a JSON file.

It prevents different kinds of planning information from being handled by the wrong part of the documentation pipeline.

gsd-doc-classifier — Agent for Claude Code by Oisinwang

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.

Clone the repo

git clone --depth 1 https://github.com/Oisinwang/get-shit-done-codex

Made for: Claude Code.

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/agents/oisinwang/get-shit-done-codex/gsd-doc-classifier.svg)](https://agentmods.dev/agents/oisinwang/get-shit-done-codex/gsd-doc-classifier)

Your own site

<a href="https://agentmods.dev/agents/oisinwang/get-shit-done-codex/gsd-doc-classifier"><img src="https://agentmods.dev/badge/agents/oisinwang/get-shit-done-codex/gsd-doc-classifier.svg" alt="Measured on agentmods" height="20"></a>

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 1,863 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.

Origin 92% 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.

Model	Per session	Once invoked
Fable 5.1	$0.00062	$0.01863
Opus 5	$0.00031	$0.00932
Sonnet 5	$0.00012	$0.00373
Haiku 4.5	$0.00006	$0.00186

Measured 6d ago against content hash 164414c4fe21, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 6d 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

92% identical to gsd-doc-classifier — 70 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.

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-*.md…9999-*.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.

6d ago First seen · 169 lines · 62 tokens per session scan A 164414c4fe21

Subscribe to this mod's changes

gsd-doc-classifier is an agent published in the GitHub repository Oisinwang/get-shit-done-codex (1 stars, last pushed 2mo ago), licensed MIT. It adds 62 tokens to every session and 1,863 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to gsd-doc-classifier, differing in 70 lines, and is treated as a copy.

Documents Planning ai-coding codex context-engineering developer-tools openai-codex spec-driven-development

ijfw-doc-verifier

Verify factual claims in generated docs against live code. Trigger after doc generation in plan/handoff/CHANGELOG steps.

FerroxLabs/ijfw · 29 tokens

docs

Use when code needs documentation - API docs, architecture diagrams, user guides, ADRs, JSDoc/TSDoc comments, or onboarding materials.

herbert-julio-azion/specialist-agent · 32 tokens

scribe

Dual-mode doc worker for scan/process batches. Returns JSON only.

rp1-run/rp1 · 15 tokens