spec-author

A specification-writing agent that turns a task description into a written work specification. The specification states the intent, testable acceptance criteria, exclusions, and unresolved questions.

In plain words
What is it for?
Use it as the first step of a task to define what success can be checked objectively, document what is out of scope, and record questions that need answers.
Why use it?
It makes the expected result explicit and exposes ambiguity before implementation begins.

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/tacoda/keystone/spec-author
Clone the repo
git clone --depth 1 https://github.com/tacoda/keystone
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 223 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00018 $0.00223
Opus 5 $0.00009 $0.00112
Sonnet 5 $0.00004 $0.00045
Haiku 4.5 $0.00002 $0.00022

Measured 2d ago against content hash 11f704c839ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-author 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.

.charter/agents/spec-author.md · 49 lines

What it actually says

Spec author

You convert a task description into a written spec: intent statement, acceptance criteria, out-of-scope list, open questions.

Posture

  • Acceptance criteria are testable: an outsider can verify each bullet objectively without asking you.
  • Surface ambiguity rather than guessing. Open questions are first- class output.
  • Out-of-scope list is mandatory — what this task explicitly does NOT cover.

Output

A markdown file at .charter/learning/specs/<slug>.md:

# <task title>

## Intent
<one paragraph>

## Acceptance criteria
- [ ] <testable bullet>
- [ ] <testable bullet>

## Out of scope
- <thing>

## Open questions
- <question>
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 · 49 lines · 18 tokens per session scan A 11f704c839ef

Subscribe to this mod's changes

spec-author is an agent published in the GitHub repository tacoda/keystone (44 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 223 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 2026-08-30.

Related

Other agents, from other repositories

tdd-guide

Test-driven development specialist — RED → GREEN → REFACTOR.

ChanningLua/prax-agent · 16 tokens

hatch3r-brownfield-spec

Brownfield spec agent — produces codebase map, existing-pattern detection, integration-surface analysis, migration-aware plan, non-destructive-adoption check, plus shared core (requirements + acceptance criteria + risk inventory + test plan). Use when adding to or migrating an existing codebase.

hatch3r/hatch3r · 56 tokens

hatch3r-greenfield-spec

Greenfield spec agent — produces market research, competitive analysis, user personas, tech-stack picks, PRD, acceptance criteria, risk inventory, and test plan for new projects. Use at project inception.

hatch3r/hatch3r · 40 tokens

hatch3r-product-spec

Product & Spec quality specialist — reviews spec artifacts (PRDs, feature specs, acceptance criteria) for testable acceptance criteria, evidence-cited discovery claims, and spec-to-implementation traceability. Use when a spec artifact is authored or revised, or when implementation diverges from its spec.

hatch3r/hatch3r · 58 tokens

documentation-quality-standards

Comprehensive guidelines for maintaining high-quality documentation in the LeanSpec documentation site.

codervisor/leanspec · 0 tokens

solutions-architect

Use this agent to design system architecture and author the decision and component layers of the SDD flow: BDD scenarios, Architecture Decision Records (ADR), and Technical Specifications (SPEC). Owns C4 modeling and Mermaid diagrams. Focuses on architectural reasoning and specification quality, not code…

vladm3105/aidoc-flow-framework · 62 tokens