turnstile-review

turnstile-review is a skill for Claude Code from febradc-github/turnstile. It costs 88 tokens per session (1,115 once invoked), scanned A, original, MIT.

A review step that sends completed work to an independent reviewer and commits the changes only when the reviewer gives a pass. It checks whether the work meets the ticket's acceptance criteria, meaning the conditions that define completion.

In plain words
What is it for?
Use it to review an in-progress ticket against its specification, resume an interrupted review, and commit work after an independent done verdict.
Why use it?
It prevents the person who wrote the code from being the only person deciding that the task is finished.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions Claude Code.

Part of the turnstile plugin — 24 skills, 23 commands, 5 agents, 3 hooks, 1 MCP server shipped together

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.

agentmods
npx agentmods add skills/febradc-github/turnstile/turnstile-review
Any agent
npx skills add febradc-github/turnstile --skill turnstile-review
Clone the repo
git clone --depth 1 https://github.com/febradc-github/turnstile

Made for: Claude Code.

Or install turnstile, the plugin that ships this one along with the rest of its 24 skills, 23 commands, 5 agents, 3 hooks, 1 MCP server.

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 turnstile-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/febradc-github/turnstile/turnstile-review.svg)](https://agentmods.dev/skills/febradc-github/turnstile/turnstile-review)
Your own site
<a href="https://agentmods.dev/skills/febradc-github/turnstile/turnstile-review"><img src="https://agentmods.dev/badge/skills/febradc-github/turnstile/turnstile-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,115 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00088 $0.01115
Opus 5 $0.00044 $0.00558
Sonnet 5 $0.00018 $0.00223
Haiku 4.5 $0.00009 $0.00112

Measured 5d ago against content hash ce2332245718, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

turnstile-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 5d 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/turnstile-review/SKILL.md · 32 lines

How it starts

The opening of the file, as written. The whole thing — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review

Process

  1. Look up <id> (from $ARGUMENTS) in the current sprint -- turnstile/sprint.yml, or (legacy) the root turnstile/sprint-<N>.yml with sprint.status: active. Not found, or status not in_progress/review: refuse and say what to do instead (/turnstile:work <id> first; /turnstile:sprint-plan if no active sprint). status: review means a prior review session was interrupted -- say so and resume from step 3. Not a git repository, or no commits yet: tell the user review needs git history to scope the diff; suggest git init and an initial commit -- never review an unscoped file tree.
  2. Set the item's status to review.
  3. Read the ticket's criteria, first match wins (<n> from <id> = C-<n>): the spec turnstile/specs/SP-<n>.md; the solo-profile plan turnstile/plans/PL-<n>.md (its "## Acceptance criteria" section); legacy spec names (turnstile/specs/<id>-*-spec.md, turnstile/specs/<id>.md); the item note's "## Acceptance criteria" section (quick-lane items). This per-ticket fallback chain is what makes switching profile mid-project safe. Criteria in none of these: refuse -- the item cannot be reviewed.
  4. Get the ticket's diff (git diff / git status against the last commit). Work enforces one in_progress item, so this diff should be exactly this ticket's changes; on unrelated uncommitted changes, stop and ask the user.
  5. Dispatch the turnstile-reviewer agent, passing only the acceptance criteria and the diff -- no implementation-session narrative or reasoning.
  6. FAIL verdict: set status back to in_progress, append the agent's per-criterion reasons to the item's notes, tell the user what needs to change. Do not commit.
  7. PASS verdict:
    • Set the item's status to done.
    • If the item has a parent, check every child of that parent (across turnstile/backlog.yml, turnstile/sprint.yml, turnstile/sprints/*.yml; match parent: <parent-id>). All done (ignoring dropped): set the parent to done in turnstile/backlog.yml and tell the user; cascade the check one level up if that parent has a parent. This rollup is the one exception to "only the reviewer marks done" -- each child was individually reviewer-certified.
    • Capture (per the capture config): in gates mode (default), dispatch brain-curator once with bounded input -- the ticket (id, title), its acceptance criteria, and the diff -- to write any decision notes this ticket produced and create or update turnstile/code/ notes for the files the diff touched. Include the estimate-mismatch observation below in the same dispatch when it applies. In opportunistic mode, dispatch only for the mismatch case.
    • Estimate mismatch: compare points against the coarse actual-effort signals on hand -- carryovers and the count of "work pass" notes entries. carryovers > 0, or 3+ work passes against 3 points or less (or an equivalent clear mismatch), is a candidate process learning for brain-curator. Never claim wall-clock timing -- only these coarse counts.
    • Stage the changed files together with the updated sprint file (so the done status lands in the same commit as the implementation), plus turnstile/backlog.yml on a parent rollup, and commit: git commit -m "<verb>: <title> (<id>)" per the brain skill's convention (no Anthropic/Claude co-author tag, no --no-verify).
    • Tell the user the ticket is done and committed.

Read the full file on GitHub · 32 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. 5d ago First seen · 32 lines · 88 tokens per session scan A ce2332245718

Subscribe to this mod's changes

turnstile-review is a skill published in the GitHub repository febradc-github/turnstile (1 stars, last pushed 1mo ago), licensed MIT. It adds 88 tokens to every session and 1,115 once invoked, about $0.0004 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

chief-strategy-officer

Owns where the business plays and how it wins over a multi-year horizon — portfolio choices, corporate development, strategic partnerships, and planning under uncertainty. Use this for a decision about which markets or businesses to be in, whether to build, buy, or partner, how to allocate capital across business…

cbrock84/headcount · 93 tokens

seo-strategy

Audits and improves organic search performance — technical health, site architecture, internal linking, structured data, and the content decisions that determine what can rank. Use this to run an SEO audit, diagnose why pages are not ranking or were deindexed, plan a site's URL and navigation structure, add structured…

cbrock84/headcount · 74 tokens

youtube-producer

Plans, packages, and scripts long-form video for retention and channel growth — idea selection, titles and thumbnails, script structure, and diagnosing why a video or channel underperforms. Use this for video ideas, packaging, scripting, a retention teardown, or channel strategy — including when someone describes a…

cbrock84/headcount · 86 tokens

chief-revenue-officer

Owns the revenue engine end to end: sales, monetization, pricing, customer success, retention, and partnerships. Use this for pricing and packaging decisions, sales strategy and coverage, forecast and pipeline health, churn and expansion, partner and channel strategy, or when marketing-sourced demand is not…

cbrock84/headcount · 80 tokens

support-operations

Designs and runs the support function — channels, queues, routing, staffing, service levels, quality, and the metrics that show whether it is working. Use this to set up or fix support operations, choose channels, size a team, set or renegotiate service levels, reduce cost per contact, diagnose long queues or poor…

cbrock84/headcount · 77 tokens

ai-ml-governance

Governs models and AI systems in production — intended use, evaluation, monitoring, human oversight, documentation, and the decision to deploy or retire. Use this before deploying a model or AI feature, when defining evaluation criteria, when a model's behavior has drifted, when assessing AI risk or regulatory…

cbrock84/headcount · 83 tokens