code: Skill for Claude Code

.specify/extensions/superspec/.specify-dev/agent-commands/claude/speckit-superspec-review/SKILL.md

speckit-superspec-review is a skill for Claude Code, Codex from HelixDevelopment/code. It costs 22 tokens per session (461 once invoked), scanned A, original, MIT.

A code-review command that compares an implementation with its written feature requirements, project rules, edge cases, and tests.

In plain words
What is it for?
Use it to review a feature, selected files, or all changes and report high-confidence findings.
Why use it?
It helps find missing requirements, bugs, security problems, weak error handling, and missing coverage before the work is considered complete.

Skill for Claude CodeCodex

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

This is HelixDevelopment/code's own configuration. It tells Claude Code and Codex how to work on code 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 code configures →

Reuse

Borrowing it

Nothing to install: this file belongs to HelixDevelopment/code. 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/HelixDevelopment/code/main/.specify/extensions/superspec/.specify-dev/agent-commands/claude/speckit-superspec-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/HelixDevelopment/code

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 speckit-superspec-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/helixdevelopment/code/speckit-superspec-review/github.svg)](https://agentmods.dev/skills/helixdevelopment/code/speckit-superspec-review)
Your own site
<a href="https://agentmods.dev/skills/helixdevelopment/code/speckit-superspec-review"><img src="https://agentmods.dev/badge/skills/helixdevelopment/code/speckit-superspec-review/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 speckit-superspec-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/helixdevelopment/code/speckit-superspec-review"><img src="https://agentmods.dev/badge/skills/helixdevelopment/code/speckit-superspec-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 461 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 $0.00022 $0.00461
Opus 5 $0.00011 $0.00230
Sonnet 5 $0.00004 $0.00092
Haiku 4.5 $0.00002 $0.00046

Measured 4d ago against content hash 095da1559e74, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

speckit-superspec-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 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.

.specify/extensions/superspec/.specify-dev/agent-commands/claude/speckit-superspec-review/SKILL.md · 60 lines

What it actually says

speckit.superspec.review

Run code review against spec requirements using review skills.

Usage

/speckit.superspec.review [scope]

Scope: Optional file paths, spec number, or "all changes". Defaults to the latest feature.

Process

  1. Read the spec and plan for the feature being reviewed
  2. Superpowers detection: Check for requesting-code-review skill
    • If found: Read the skill and follow its pre-evaluation checklist and review dispatch protocol
    • If not found: Use the built-in review protocol below
  3. Built-in review protocol:
    • Spec compliance: Verify each acceptance scenario from the spec is implemented
    • Edge case coverage: Verify brainstormed edge cases are handled
    • Constitution compliance: Check all governance principles are respected
    • Code quality: Check for bugs, security issues, error handling
    • Test coverage: Verify tests exist for critical paths
  4. Report findings with confidence scores (0-100, only report issues >= 80)
  5. Group findings by severity: Critical > Important > Suggestion

Output

Review findings reported to user. Optionally written to specs/NNN-feature-name/checklist-review.md.

Finding Format

Each finding includes:

  • Clear description with confidence score
  • File path and line reference
  • Specific recommendation or fix suggestion

Findings below 80 confidence are suppressed to reduce noise.

Superpowers Adaptation

When using the requesting-code-review skill, adapt its outputs:

  • Add superspec-specific review dimensions: spec compliance, constitution compliance, brainstorm coverage
  • Output location → report to user, optionally write to checklist file

See .specify/extensions/superspec/references/superpowers-bridge.md for full adaptation rules.

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 · 60 lines · 22 tokens per session scan A 095da1559e74

Subscribe to this mod's changes

speckit-superspec-review is a skill published in the GitHub repository HelixDevelopment/code (2 stars, last pushed 3d ago), licensed MIT. It adds 22 tokens to every session and 461 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 2026-09-04.

Related

Other skills, from other repositories

hqe

Comprehensive codebase health auditing, remediation, and verification skill based on the canonical HQE Protocol v5.0.0.

spearchucker667/Skill-HQE · 29 tokens

simplify-code

Sequential 3-lens cleanup of recent code changes.

HezaoHezao/poirot · 15 tokens

hunk-extensions

Maps the hunkdiff/extension authoring surface for Hunk, the terminal diff viewer — hiding or reordering reviewed files, docked panes, alternate file views, commands and key bindings, dialogs, workspace writes, themes, syntax languages, VCS backends, lifecycle events. Use when writing, debugging, or installing a Hunk…

modem-dev/hunk · 105 tokens

sage-review

Deep, platform-neutral code review for PRs and CRs in ONE thorough single pass — design reasoning (Problem Worth Solving & Solution Fit) as one dimension alongside the 9 code-level dimensions, with chain-of-consequences, self-critique, and draft-only comments. The single app-owned source of truth.

kirodotdev/KiroCrew · 68 tokens

rubber-duck

Adversarial "rubber duck" review that turns explaining-out-loud into a hallucination check. The main session is the PRESENTER (it did the work — a design doc, investigation, or analysis — and holds the real reasoning) and reconstructs the topic to a LISTENER — a spawned subagent pinned to a DIFFERENT-vendor model that…

kirodotdev/KiroCrew · 161 tokens

learn-from-sage

Detection-gap (miss) analysis for Code Review Sage. Learn from shipped fixes, acted-on human comments, and design outcomes to close reviewer blind spots. Inline during review stages a candidate; a human triggers a one-shot AI consolidation into the live ruleset.

kirodotdev/KiroCrew · 56 tokens