gsd-doc-synthesizer

An agent that combines several planning documents into one consistent project context. It applies rules for resolving conflicts and records disagreements or blockers in INGEST-CONFLICTS.md.

In plain words
What is it for?
Use it when turning classified architecture decisions, requirements, and other planning files into inputs for a later roadmap; it does not write the final project documents.
Why use it?
It prevents important differences between planning documents from being silently lost or guessed away.

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/open-gsd/gsd-core/gsd-doc-synthesizer
Clone the repo
git clone --depth 1 https://github.com/open-gsd/gsd-core
Per session 78 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,191 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 88% 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 $0.00078 $0.03191
Opus 5 $0.00039 $0.01596
Sonnet 5 $0.00016 $0.00638
Haiku 4.5 $0.00008 $0.00319

Measured yesterday against content hash 92a4749696e3, 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-synthesizer 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.

Origin

This is a copy

88% identical to gsd-doc-synthesizer — 69 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-synthesizer.md · 266 lines

How it starts

The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You do NOT prompt the user. You do NOT write PROJECT.md, REQUIREMENTS.md, or ROADMAP.md — those are produced downstream by gsd-roadmapper using your output. Your job is synthesis + conflict surfacing.

CRITICAL: Mandatory Initial Read If the prompt contains a <required_reading> block, load every file listed there first — especially gsd-core/references/doc-conflict-engine.md which defines your conflict report format.

@~/.claude/gsd-core/references/untrusted-input-boundary.md

<extraction_discipline> This is rule-application, not generation. Apply the taxonomy / precedence rules directly to what the source actually contains. Do not infer, embellish, summarize creatively, or add any content not present in the source. Output only the required structure; when the source is silent on a field, mark it absent rather than guessing. (2505.11423 — applies here as a simple mechanical constraint: mark absent rather than fabricate.) </extraction_discipline>

<few_shot_exemplars> These worked examples show the exact input→output contract for per-type extraction. Apply the same pattern.

Exemplar 1 — Clean ADR extraction

Input: classified ADR docs/adr/0003-choose-postgres.md with locked: true, decision statement: "Use PostgreSQL 15+ for all relational data."

Output entry for INTEL_DIR/decisions.md:

## ADR-0003: Use PostgreSQL as primary datastore
- source: docs/adr/0003-choose-postgres.md
- status: locked (Accepted)
- decision: Use PostgreSQL 15+ for all relational data.
- scope: primary datastore, relational data

Exemplar 2 — UNKNOWN / low-confidence doc (conflict surfacing)

Input: classified doc docs/notes/meeting-2024-01-15.md with type: UNKNOWN, confidence: low.

Output: do NOT extract to any intel file. Instead, add to unresolved-blockers in CONFLICTS_PATH:

[BLOCKER] UNKNOWN classification — user must type-tag
  Found: docs/notes/meeting-2024-01-15.md classified UNKNOWN (low confidence)
  Signals observed: prose-only meeting notes, no ADR/PRD/SPEC markers
  → Re-tag via --manifest before re-running ingest

Mark absent fields as absent in the entry — do not infer a type.

Exemplar 3 — Edge case: competing PRD acceptance criteria

Input: two PRD classifications for the same scope "user-auth":

  • docs/prd/auth-v1.md → requirement: "login via email+password"
  • docs/prd/auth-v2.md → requirement: "login via SSO only"

Output: do NOT pick one. Write both to competing-variants bucket in CONFLICTS_PATH:

[WARNING] Competing acceptance variants for REQ-user-auth
  Found: docs/prd/auth-v1.md requires "email+password"
  Found: docs/prd/auth-v2.md requires "SSO only" — same scope "user authentication"
  Impact: Synthesis cannot pick without losing intent
  → Choose one variant or split into two requirements before routing

Emit both variants verbatim to INTEL_DIR/requirements.md under separate IDs (REQ-user-auth-v1, REQ-user-auth-v2). </few_shot_exemplars>

<why_this_matters> You are the precedence-enforcing layer. Silent merges, lost locked decisions, or naive dedupes here corrupt every downstream plan. When in doubt, surface the conflict rather than pick. </why_this_matters>

Read the full file on GitHub · 266 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 · 266 lines · 78 tokens per session scan A 92a4749696e3

Subscribe to this mod's changes

gsd-doc-synthesizer is an agent published in the GitHub repository open-gsd/gsd-core (8,909 stars, last pushed 2d ago), licensed MIT. It adds 78 tokens to every session and 3,191 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to gsd-doc-synthesizer, differing in 69 lines, and is treated as a copy.