gate-spec

gate-spec is a skill for Claude Code, Codex from Obsidian-Owl/specwright. It costs 33 tokens per session (948 once invoked), scanned A, original, MIT.

A compliance check that connects every acceptance criterion in a specification to supporting code and tests. An acceptance criterion is a specific condition the finished work must satisfy.

In plain words
What is it for?
It builds a file-and-line evidence matrix for specification criteria and, where applicable, behavioral integration criteria, then records the result.
Why use it?
It reveals requirements that have no implementation proof or test proof, so incomplete work cannot appear complete.

Skill for Claude CodeCodex

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 skills/obsidian-owl/specwright/gate-spec
Any agent
npx skills add Obsidian-Owl/specwright --skill gate-spec
Clone the repo
git clone --depth 1 https://github.com/Obsidian-Owl/specwright

Made for: Claude Code, Codex.

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 gate-spec

README.md
[![agentmods](https://agentmods.dev/badge/skills/obsidian-owl/specwright/gate-spec.svg)](https://agentmods.dev/skills/obsidian-owl/specwright/gate-spec)
Your own site
<a href="https://agentmods.dev/skills/obsidian-owl/specwright/gate-spec"><img src="https://agentmods.dev/badge/skills/obsidian-owl/specwright/gate-spec.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 948 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 $0.00033 $0.00948
Opus 5 $0.00016 $0.00474
Sonnet 5 $0.00007 $0.00190
Haiku 4.5 $0.00003 $0.00095

Measured 4d ago against content hash ba157ee86372, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gate-spec 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 4d 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.

core/skills/gate-spec/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gate: Spec Compliance

Goal

Prove that the implementation actually does what was asked for. Every acceptance criterion in the spec must map to implementation evidence (file:line) and test evidence (test name at file:line). This is the gate that closes the loop.

Inputs

  • {workDir}/spec.md -- acceptance criteria
  • {repoStateRoot}/work/{selectedWork.id}/workflow.json -- selected work unit
  • The codebase (implementation and tests)

Outputs

  • Evidence file at {workDir}/evidence/spec-compliance.md
  • Compliance matrix: each criterion → implementation ref + test ref + status
  • Gate status in the selected work's workflow.json
  • The compliance matrix remains the canonical AC / IC proof surface that downstream review-packet.md synthesis summarizes or references

Constraints

Criteria extraction (LOW freedom):

  • Parse spec.md for all acceptance criteria (lines matching - [ ] AC-*).
  • Number them. Every single one must be mapped. No skipping.
  • On the final work unit of a multi-WU design: also parse behavioral integration criteria (IC-B{n} entries) from integration-criteria.md in the design-level directory. IC-B entries are added to the compliance matrix alongside ACs. When not on the final work unit, when integration-criteria.md does not exist, or when integration-criteria.md has no IC-B entries, gate-spec operates exactly as before — no behavioral IC mapping.

Evidence mapping (HIGH freedom):

  • For each criterion, search the codebase for implementation evidence.
  • For each criterion, search test files for test evidence.
  • Delegate to specwright-reviewer for thorough analysis if needed.
  • For behavioral criteria (execution-path claims, not structural checks), trace premises from the spec and code, derive claims from those premises, and draw conclusions without adding uncited evidence.
  • Evidence must be specific: file path and line number, not "somewhere in src/".

Verdict (LOW freedom):

  • Follow protocols/evidence.md#verdict-rendering.
  • Criterion with both implementation AND test evidence = PASS.
  • Criterion with implementation but no test = WARN.
  • Criterion with neither = FAIL.
  • Overall: if ANY criterion is FAIL, gate is FAIL.
  • IC-B entries (when present): IC-B with both implementation and test evidence = PASS. IC-B without test evidence = FAIL (gate-spec's standard verdict vocabulary). Note: gate-spec FAIL for IC-Bs and deliverable verification BLOCK for IC-Bs are complementary — gate-spec reports the finding within its standard framework, deliverable verification enforces the action. gate-spec runs first (as part of the 6 standard gates); deliverable verification runs after all gates.
  • Reference discovered behaviors at INFO level per protocols/build-quality.md. Does not alter PASS/WARN/FAIL verdict.

Read the full file on GitHub · 101 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. 4d ago First seen · 101 lines · 33 tokens per session scan A ba157ee86372

Subscribe to this mod's changes

gate-spec is a skill published in the GitHub repository Obsidian-Owl/specwright (9 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 948 once invoked, about $0.0002 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 skills, from other repositories

rust-skills

Rust best practices — 179 rules across 14 categories for idiomatic, optimized Rust code.

martineserios/thebrana · 23 tokens

new-skill

Scaffold a new brooks-lint analysis skill so it passes npm run validate and npm run evals on the first try — generates skills/{name}/SKILL.md (with the mandatory "Do NOT trigger for:" clause and a Process section citing guide step ranges) plus skills/{name}/{name}-guide.md (sequentially numbered steps), then appends…

hyhmrright/brooks-lint · 145 tokens

cco-task

Organize work by task, track tokens/cost per task, and keep a small patchable execution state that is re-injected after /compact (SKILL.state-style) — start a task, patch its state, list tasks, or mark the active one done. Pairs with /cco-pack to load minimal context per task.

egorfedorov/claude-context-optimizer · 70 tokens

cco-templates

Manage context templates for common task types.

egorfedorov/claude-context-optimizer · 11 tokens

discuss

Use when exploring a feature idea before committing, or revisiting a parked one. Triggers — "/engineer.discuss", "/engineer.discuss ", "I have an idea about", "should we build", "let's think about".

swingerman/engineer · 54 tokens

prompt-tuning

Tune a prompt, or anything whose quality is measured by non-deterministic model output, without chasing noise - a noise baseline before the first edit, medians over repeated runs, enforcement AFTER generation rather than in the wording. Use when iterating on prompts or model-judged output.

jjanczur/tyran · 58 tokens