spec-synthesizer

spec-synthesizer is an agent for Claude Code from edloidas/skills. It costs 75 tokens per session (1,741 once invoked), scanned A, original, MIT.

A documentation agent that combines reports from other code-analysis agents into a final software specification. It creates Markdown files describing the system, its parts, and their connections.

In plain words
What is it for?
Use it at the end of a code-to-spec process to produce files such as README.md, architecture.md, modules.md, contracts.md, and individual module documents.
Why use it?
It removes the need to manually merge overlapping analysis from several agents. It keeps source citations and carries forward data shapes from the earlier reports.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the review plugin — 6 skills, 6 agents shipped together

Good fit Use it at the end of a code-to-spec process to produce files such as README.md, architecture.md, modules.md, contracts.md, and individual module documents.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/edloidas/skills/spec-synthesizer
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/edloidas/skills

Made for: Claude Code.

Or install review, the plugin that ships this one along with the rest of its 6 skills, 6 agents.

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.

agentmods badge for spec-synthesizer

README.md
[![agentmods](https://agentmods.dev/badge/agents/edloidas/skills/spec-synthesizer.svg)](https://agentmods.dev/agents/edloidas/skills/spec-synthesizer)
Your own site
<a href="https://agentmods.dev/agents/edloidas/skills/spec-synthesizer"><img src="https://agentmods.dev/badge/agents/edloidas/skills/spec-synthesizer.svg" alt="Measured on agentmods" height="20"></a>
Per session 75 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,741 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 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 5.1 $0.00075 $0.01741
Opus 5 $0.00037 $0.00870
Sonnet 5 $0.00015 $0.00348
Haiku 4.5 $0.00007 $0.00174

Measured 8d ago against content hash 8e7524f0ba24, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

spec-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 8d 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.

review/agents/spec-synthesizer.md · 224 lines

How it starts

The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the spec synthesizer. Your mission is to take the raw outputs from upstream agents (scout, module analyzers, contract resolver, deep analyzers, auditor) and assemble the final spec directory.

You do not read source files. You do not re-analyze. Your job is pure aggregation: read the upstream text outputs, normalize terminology, resolve overlap, and write the final markdown files in the destination directory.

Core Principles

  1. Aggregation only. Do not introduce new claims. Every statement in your output must trace to an upstream agent's output.
  2. Preserve evidence. Every file:line citation from upstream survives unchanged to the final output.
  3. Normalize terminology. If module analyzers used different wording for the same concept, pick one and apply it consistently. Do not change citations.
  4. Preserve literal payloads. Payload shapes from upstream are carried through verbatim.
  5. No placeholders. Every section in every file is complete.
  6. No product names. Scan for and remove any stack-specific names that leaked through upstream.

Inputs

Your prompt will contain:

  • Destination directory (absolute path, e.g. /abs/path/docs/spec/).
  • Tier (Medium or Large).
  • Bundle summary (file count, LOC, detected languages, tier, invocation mode).
  • Absolute paths to upstream output files:
    • scout.md
    • modules/<module-name>.md (one per module summary, multiple)
    • contracts.md
    • deep/<module-name>.md (one per flagged critical module, multiple; may be empty list)
    • audit-global.md and audit/<module-name>.md (multiple)

Workflow

Step 1: Read all upstream outputs

Use Read on every upstream file listed in your prompt.

Step 2: Plan the output directory

Files to create in the destination:

  • README.md — bundle summary, tier, how to read the spec.
  • architecture.md — derived from scout output.
  • modules.md — module catalog table + per-module medium-depth summaries.
  • contracts.md — derived from contract resolver output.
  • audit.md — consolidated audit findings (global + per-module).
  • modules/<module-name>.md — for each flagged critical module, the deep 11-section spec.

Read the full file on GitHub · 224 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. 8d ago First seen · 224 lines · 75 tokens per session scan A 8e7524f0ba24

Subscribe to this mod's changes

spec-synthesizer is an agent published in the GitHub repository edloidas/skills (2 stars, last pushed yesterday), licensed MIT. It adds 75 tokens to every session and 1,741 once invoked, about $0.0004 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 agents, from other repositories

reviewer

A code-review agent that examines changes for correctness, readability, testing, security, consistency, and traceability.

Insajin/autopus-adk · 42 tokens

code-reviewer

Use this agent when you need to review code changes for correctness, discovered project-convention compliance, and duplicated logic. Invoke proactively after writing or modifying code, and before committing or opening a pull request. Reviews an explicit diff, pull request, or named file set; defaults to the…

rjmurillo/ai-agents · 70 tokens

issue-feature-review

Review GitHub feature requests with constructive skepticism. Summarize the ask, evaluate user impact and implementation cost, flag unknowns, and provide a recommendation with actionable next steps.

rjmurillo/ai-agents · 39 tokens

comment-analyzer

Use this agent when you need to analyze code comments for accuracy, completeness, and long-term maintainability. Use cases include large documentation comments or docstrings, pull requests that add or modify comments, technical debt or comment rot review, and checks that comments match the code they describe.

rjmurillo/ai-agents · 60 tokens

pr-test-analyzer

Use this agent when you need to review a pull request for test coverage quality and completeness. This agent should be invoked after a PR is created or updated to ensure tests adequately cover new functionality and edge cases.

rjmurillo/ai-agents · 46 tokens

type-design-analyzer

Use this agent when you need expert analysis of type design in your codebase. Use cases include introducing a new type, reviewing all types added by a pull request, and refactoring existing types to improve their design quality. The agent provides qualitative feedback and quantitative ratings on encapsulation…

rjmurillo/ai-agents · 69 tokens