review-design-contracts

review-design-contracts is a skill for Codex from PANYUXIN6/pyx-skills. It costs 115 tokens per session (2,551 once invoked), scanned A, original, MIT.

A structured reviewer for Markdown design documents and accepted fix queues. It checks the design, challenges its assumptions, and can separately apply or verify fixes.

In plain words
What is it for?
Reviewing a new design, consuming an approved list of fixes, or independently checking an edited design with evidence and risk-based follow-up.
Why use it?
It helps catch unclear contracts, architecture mistakes, and unproven fixes before implementation. It also keeps review, editing, and verification as separate steps.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Codex; $skill-name invocation.

Good fit Reviewing a new design, consuming an approved list of fixes, or independently checking an edited design with evidence and risk-based follow-up.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/panyuxin6/pyx-skills/review-design-contracts
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 PANYUXIN6/pyx-skills --skill review-design-contracts
Clone the repo
git clone --depth 1 https://github.com/PANYUXIN6/pyx-skills

Made for: 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 review-design-contracts

README.md
[![agentmods](https://agentmods.dev/badge/skills/panyuxin6/pyx-skills/review-design-contracts/github.svg)](https://agentmods.dev/skills/panyuxin6/pyx-skills/review-design-contracts)
Your own site
<a href="https://agentmods.dev/skills/panyuxin6/pyx-skills/review-design-contracts"><img src="https://agentmods.dev/badge/skills/panyuxin6/pyx-skills/review-design-contracts/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for review-design-contracts

Your own site · 80×15
<a href="https://agentmods.dev/skills/panyuxin6/pyx-skills/review-design-contracts"><img src="https://agentmods.dev/badge/skills/panyuxin6/pyx-skills/review-design-contracts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 115 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,551 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 85
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
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 $0.00115 $0.02551
Opus 5 $0.00057 $0.01275
Sonnet 5 $0.00023 $0.00510
Haiku 4.5 $0.00012 $0.00255

Measured 12d ago against content hash 975e02d5824f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

review-design-contracts 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 12d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/review-design.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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-design-contracts/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Design Contracts

Run a quality-first design review without model voting or LLM-as-judge. Keep the target document unchanged throughout the review.

Select one operation

Choose exactly one mode from the user's explicit request and do not transition between modes implicitly:

  • review: run a new design review and leave the target unchanged.
  • apply-fixes: validate and consume an accepted queue, edit the target, then stop and hand off to a separate reviewer task.
  • verify-fixes: independently review an already edited target. Enter this mode only when the current task is explicitly asked to run verify-fixes and did not edit that target.

Completing apply-fixes never authorizes the same task to enter verify-fixes, even when the queued run directory is available.

Start a review

  1. Read references/review-protocol.md.
  2. Confirm the current Codex task exposes Native spawn_agent, wait_agent, and interrupt_agent. If any is unavailable, stop before creating a run. Do not fall back to a CLI or API model backend.
  3. Resolve <skill-directory> as the absolute directory containing this SKILL.md.
  4. Run the authority precheck in references/review-protocol.md. Inspect the target's frontmatter and direct design links first. If the target identifies itself as a child or delegates a material contract without a resolvable path, perform only the bounded same-directory and declared-index search described there. Automatically include an unambiguous non-observed governing design backed by a direct relationship; otherwise treat the target as self-contained unless an unresolved external contract is material to the review. Do not invoke another skill for this precheck.
  5. Check docs/REPO_MAP.md and docs/ARCHITECTURE.md in the target repository. If either is missing, invoke $repo-map-first in repository-context bootstrap mode. If relevant map claims may be stale or contradictory, invoke repository-context validation mode. Preserve the review target and authority provenance. Observed maps may locate files but cannot establish normative authority. If repository context required for architecture review remains materially ambiguous, stop before creating a run and report INSUFFICIENT_INPUT.
  6. From the repository root, run:

Read the full file on GitHub · 143 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. 12d ago First seen · 143 lines · 115 tokens per session scan A 975e02d5824f

Subscribe to this mod's changes

review-design-contracts is a skill published in the GitHub repository PANYUXIN6/pyx-skills (6 stars, last pushed 6d ago), licensed MIT. It adds 115 tokens to every session and 2,551 once invoked, about $0.0006 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.