correct-spec

correct-spec is a skill for Claude Code, Codex from orin-dx/agent-plugins. It costs 34 tokens per session (430 once invoked), scanned A, original, MIT.

A review tool that checks whether a written software specification matches the requirement it came from. A specification describes what should be built and how success will be tested.

In plain words
What is it for?
Compare a draft specification with its source requirement and optional research report.
Why use it?
It helps find acceptance criteria that were added, changed, or misunderstood before implementation begins.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Compare a draft specification with its source requirement and optional research report.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/orin-dx/agent-plugins/correct-spec
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.

Any agent
npx skills add orin-dx/agent-plugins --skill correct-spec
Clone the repo
git clone --depth 1 https://github.com/orin-dx/agent-plugins

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 correct-spec

README.md
[![agentmods](https://agentmods.dev/badge/skills/orin-dx/agent-plugins/correct-spec.svg)](https://agentmods.dev/skills/orin-dx/agent-plugins/correct-spec)
Your own site
<a href="https://agentmods.dev/skills/orin-dx/agent-plugins/correct-spec"><img src="https://agentmods.dev/badge/skills/orin-dx/agent-plugins/correct-spec.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 430 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 $0.00034 $0.00430
Opus 5 $0.00017 $0.00215
Sonnet 5 $0.00007 $0.00086
Haiku 4.5 $0.00003 $0.00043

Measured today against content hash 3bdf6e3a150c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

correct-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 today.

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.

harnesses/codex/plugins/scribe/skills/correct-spec/SKILL.md · 38 lines

What it actually says

Correct a contradictory specification

Outcome

Revise only the affected criteria and dependent plan implications while preserving the spec identity, durable path, and audit trail.

Workflow

  1. Read the spec from its spec_file_path; validate it using shared/schemas/[email protected].
  2. Inspect the contradiction report and live workspace behavior. Confirm that the conflict is real rather than a missing implementation step or a misunderstood test.
  3. Identify the affected criterion and dependent criteria. Amend only the necessary text, set revision_note, and retain the same spec ID and file path.
  4. Run the corrected draft through scribe:verify-spec, scribe:audit-spec, scribe:audit-architecture, and scribe:gate-spec.
  5. After a passing gate and user authorization, overwrite the existing docs/specs/<id>.json artifact, commit it, and send its changed criterion IDs to navigator:plan in amend mode.

Contract

  • Input schema: shared/schemas/[email protected]
  • Output schema: shared/schemas/[email protected]
  • Durable path: the existing spec_file_path, normally docs/specs/<id>.json
  • Follow-on: amended shared/schemas/[email protected] must go through planning review before implementation resumes.

Teams and fallback

Before delegating, read agent-roles/README.md; use tracer only for independent contradictory paths and keep the correction itself with the primary author.

This is a narrow evidence-and-judgment task; work alone by default. Use a teammate only when the contradiction spans independent code paths, and reconcile evidence before editing the spec.

Boundaries

  • Do not correct the spec for the same criterion twice without escalating to the user.
  • Do not overwrite the persisted file or commit without user authorization.
  • Do not continue implementation against a criterion confirmed to be contradictory.
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. today Changed · +2 lines · -70 tokens per session 3bdf6e3a150c
  2. 6d ago First seen · 36 lines · 104 tokens per session scan A 7160f92f63f9

Subscribe to this mod's changes

correct-spec is a skill published in the GitHub repository orin-dx/agent-plugins (1 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 430 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.