superspecs: Skill for Claude Code

.skills/execute-review/SKILL.md

execute-review is a skill for Claude Code, Codex from fokkerone/superspecs. It costs 49 tokens per session (985 once invoked), scanned A, original, MIT.

A review step for checking completed coding tasks against their specification and code-quality expectations. It uses two passes and can stop further work when it finds a critical problem.

In plain words
What is it for?
Use it between tasks, after work by a subagent, or when a code review is requested.
Why use it?
It catches missing requirements, security issues, data-loss risks, and other serious problems while changes are still recent.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

This is fokkerone/superspecs's own configuration. It tells Claude Code and Codex how to work on superspecs itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything superspecs configures →

Reuse

Borrowing it

Nothing to install: this file belongs to fokkerone/superspecs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/fokkerone/superspecs/main/.skills/execute-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/fokkerone/superspecs

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 execute-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/fokkerone/superspecs/execute-review.svg)](https://agentmods.dev/skills/fokkerone/superspecs/execute-review)
Your own site
<a href="https://agentmods.dev/skills/fokkerone/superspecs/execute-review"><img src="https://agentmods.dev/badge/skills/fokkerone/superspecs/execute-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 985 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 $0.00049 $0.00985
Opus 5 $0.00024 $0.00492
Sonnet 5 $0.00010 $0.00197
Haiku 4.5 $0.00005 $0.00098

Measured 8d ago against content hash e3378aaf1f86, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

execute-review 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 8d 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.

.skills/execute-review/SKILL.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: execute-review

You are reviewing implementation against the spec and for code quality.

This runs between tasks. Not at the end — between each task, while changes are still small and fixable.

Critical findings block progress. No task starts after a Critical finding until it's resolved.

Severity Levels

Level Meaning Action
Critical Spec violation, security issue, data loss risk, test circumvented BLOCK. Stop all execution. Must be fixed before next task.
High Logic error, wrong behavior, missing error handling Must be resolved before wave ends
Medium Code quality issue, missed edge case, unclear abstraction Should be resolved; note in review-log
Low Style, naming, minor improvement Note in review-log; optional to fix

Two-Pass Review

Pass 1: Spec Compliance

Read superspec/specs/<slug>/spec.md. For every requirement in scope of the completed task:

## Pass 1: Spec Compliance

### ✅ Requirement: <Name>
Scenario: <Name>
Coverage: `<test-file>:<line>` — `<test name>`
Verified: behavior matches spec ✅

### ⚠️ Requirement: <Name>
Scenario: <Name>
Coverage: MISSING
Severity: Critical
Issue: This scenario has no test. The behavior is not verified.

### ❌ Requirement: <Name>
Scenario: <Name>
Coverage: `<test-file>:<line>`
Verified: FAILS — the implementation does X but spec says Y
Severity: Critical

If any Critical findings in Pass 1: stop immediately. Report. Do not run Pass 2.

Pass 2: Code Quality

Only run if Pass 1 is fully ✅ (or only Medium/Low findings).

Review dimensions:

Logic correctness

  • Are there cases where the code does the wrong thing?
  • Are error paths handled?
  • Are assumptions safe?

Test quality

  • Do tests test behavior (not implementation)?
  • Are edge cases covered?
  • Are tests readable as documentation?

Structure

  • DRY: is there duplication that should be extracted?
  • YAGNI: is there code that serves no current requirement?
  • Clarity: can this be read and understood without mental overhead?

Read the full file on GitHub · 162 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. 8d ago First seen · 162 lines · 0 tokens per session scan A e3378aaf1f86

Subscribe to this mod's changes

execute-review is a skill published in the GitHub repository fokkerone/superspecs (4 stars, last pushed 2mo ago), licensed MIT. It adds 49 tokens to every session and 985 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.