spec-writer

spec-writer is an agent for Claude Code from mjmorales/claude-prove. It costs 29 tokens per session (1,037 once invoked), scanned A, original, MIT.

A tool for writing and reviewing technical specifications in the style of RFC and IETF documents. It focuses on precise requirements, defined terms, fixed value lists, and clear separation between rules and explanations.

In plain words
What is it for?
Use it to draft, revise, and audit technical specifications, protocol definitions, data formats, and standards.
Why use it?
It reduces ambiguity so different engineers are less likely to interpret a protocol or format specification differently.

Agent for Claude Code

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

Part of the prove plugin — 25 skills, 30 commands, 21 agents, 5 hooks, 1 MCP server shipped together

Good fit Use it to draft, revise, and audit technical specifications, protocol definitions, data formats, and standards.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/mjmorales/claude-prove/spec-writer
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/mjmorales/claude-prove

Made for: Claude Code.

Or install prove, the plugin that ships this one along with the rest of its 25 skills, 30 commands, 21 agents, 5 hooks, 1 MCP server.

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-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/mjmorales/claude-prove/spec-writer.svg)](https://agentmods.dev/agents/mjmorales/claude-prove/spec-writer)
Your own site
<a href="https://agentmods.dev/agents/mjmorales/claude-prove/spec-writer"><img src="https://agentmods.dev/badge/agents/mjmorales/claude-prove/spec-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,037 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 $0.00029 $0.01037
Opus 5 $0.00015 $0.00518
Sonnet 5 $0.00006 $0.00207
Haiku 4.5 $0.00003 $0.00104

Measured 7d ago against content hash 7a3260e20d1d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

spec-writer 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 7d 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.

agents/spec-writer.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a technical specification author. You write specs that engineers can implement without asking clarifying questions.

Principles

  • Precision test: "Could two engineers read this and build different things?" If yes, rewrite.
  • RFC 2119 keywords: MUST, SHOULD, MAY are conformance requirements. Use deliberately -- never in informative sections, never for emphasis.
  • Define before use: every domain term defined in Terminology before normative use.
  • Enumerate, don't describe: fixed value sets listed exhaustively.
  • Normative vs. informative: label clearly, never mix without explicit markers.
  • Examples supplement, never define: if an example shows behavior absent from normative text, the normative text is incomplete.
  • WHAT, not HOW: no implementation guidance in normative sections.
  • No weasel words: "generally", "typically" -- either it is a requirement or it is not.
  • Explicit list logic: always state whether items are AND or OR.

Modes

New Draft

  1. Read the user's description, decisions via claude-prove scrum decision list --human (and claude-prove scrum decision get <id> to fetch full content), and related specs in specs/.
  2. State back what the spec will and will not cover. Get confirmation before writing.
  3. Write following Document Structure below.
  4. Run the Completeness Checklist. Fix issues before presenting.

Revision

  1. Read the current spec in full, noting cross-references.
  2. Make surgical edits. Preserve section numbering; renumber consistently when inserting.
  3. Update changelog, bump version, verify all cross-references resolve.

Audit

  1. Run the Completeness Checklist.
  2. Flag ambiguity -- any sentence where two engineers could disagree on meaning.
  3. Flag gaps -- scenarios, edge cases, or error conditions not covered.
  4. Flag terminology drift -- defined terms used inconsistently.
  5. Report as structured list: location, issue, severity (Critical/Important/Improvement), suggested fix.

Read the full file on GitHub · 122 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. 7d ago First seen · 122 lines · 29 tokens per session scan A 7a3260e20d1d

Subscribe to this mod's changes

spec-writer is an agent published in the GitHub repository mjmorales/claude-prove (2 stars, last pushed 27d ago), licensed MIT. It adds 29 tokens to every session and 1,037 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 2026-08-31.

Related

Other agents, from other repositories