ralph-review

ralph-review is a skill for Codex from zacharygcook/agent-skills. It costs 61 tokens per session (296 once invoked), scanned A, original, MIT.

A review skill for Ralph sprints, meaning planned software-development work divided into tracked pieces called chunks.

In plain words
What is it for?
Use it to audit a current or finished sprint, identify gaps or accidental changes, and decide whether it is complete, needs repair, or is blocked.
Why use it?
It checks whether the delivered work matches its specification and whether the reported tests, commits, documentation, and workflow records provide evidence.

Skill for Codex

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

Good fit Use it to audit a current or finished sprint, identify gaps or accidental changes, and decide whether it is complete, needs repair, or is blocked.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zacharygcook/agent-skills/ralph-review
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 zacharygcook/agent-skills --skill ralph-review
Clone the repo
git clone --depth 1 https://github.com/zacharygcook/agent-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 ralph-review

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/zacharygcook/agent-skills/ralph-review"><img src="https://agentmods.dev/badge/skills/zacharygcook/agent-skills/ralph-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 296 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 $0.00061 $0.00296
Opus 5 $0.00030 $0.00148
Sonnet 5 $0.00012 $0.00059
Haiku 4.5 $0.00006 $0.00030

Measured 11d ago against content hash 98ae2e55f20d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ralph-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 11d 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/ralph-review/SKILL.md · 23 lines

What it actually says

Ralph Review

Review the sprint as an evidence-backed delivery unit.

  1. Read repository instructions, the durable spec, sprint README.md, IMPLEMENTATION_PLAN.md, relevant-specs.md, chunks.json, and SCRATCHPAD.md.
  2. Inspect the actual commit range and changed artifacts. Do not accept summaries as proof.
  3. Verify every passed chunk against its acceptance criteria, validation logs, and commit evidence.
  4. Check final review, documentation, sprint-validation, and optional E2E hook states. Distinguish skipped, failed, interrupted, and completed hooks.
  5. Look for missing spec behavior, accidental scope, weak tests, stale documentation, unsafe orchestration state, and negative knowledge the next sprint must preserve.
  6. Report findings by severity, then give a clear verdict: complete, repairable before acceptance, or blocked. Name the exact evidence and next action.

Do not rewrite chunk state, manufacture evidence, or implement findings during a review-only request. When installed beside $ralph-loop, consult references/review.md for the full shared rubric.

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 23 lines · 61 tokens per session scan A 98ae2e55f20d

Subscribe to this mod's changes

ralph-review is a skill published in the GitHub repository zacharygcook/agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 296 once invoked, about $0.0003 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

critique-theater

Five-dimension design quality review — score the artifact against craft, brand, accessibility, and copy, then fix what falls short before handing it over.

nexu-io/open-design · 35 tokens

package-evaluator

Evaluates Claude Code package quality across 6 dimensions for all 7 package types, producing scored audit reports. Triggers on: "evaluate package", "audit agent quality", "score this hook", "package audit", "skill quality check". NOT for LLM prompts, use prompt-lab.

Mathews-Tom/armory · 64 tokens

code-refiner

Deep code simplification and refactoring preserving behavior across Python, Go, TypeScript, Rust. Targets complexity, anti-patterns, readability debt. Triggers on: "simplify this code", "refactor for clarity", "reduce complexity", "make this more readable", "tech debt cleanup", "too much nesting".

Mathews-Tom/armory · 69 tokens

package-optimizer

Evaluate one existing package or bounded package family from recorded evaluator evidence and a capability profile, then propose retain, simplify, strengthen, retire, or inconclusive without editing. Use when optimizing a skill, agent, hook, rule, command, utility, or preset; evaluating whether package detail is…

Mathews-Tom/armory · 110 tokens

plan-review

Pre-implementation plan audit stress-testing scope, assumptions, risks, and failure modes before code is written. Triggers on: "review this plan", "is this plan solid", "what am I missing", "challenge my assumptions", "stress-test this", "/plan-review".

Mathews-Tom/armory · 59 tokens

beautify-with-pingfusi

Beautify or redesign an existing website through iterative pingfusi review rounds with a real human reviewer. Use when asked to "beautify this website," "make this page look professional," "polish this UI/design," "improve the visual design," or finish an AI-built page when there is no reference site to match. Do not…

alex-durango/pingfusi · 95 tokens