turnstile-pickup

turnstile-pickup is a skill for Claude Code, Codex from febradc-github/turnstile. It costs 86 tokens per session (739 once invoked), scanned A, original, MIT.

A context-restoration command for returning to unfinished development work, including the current ticket, progress, blockers, decisions, and related notes.

In plain words
What is it for?
Use it to inspect the active sprint board, find the in-progress item, compare its requirements with the current Git changes, and surface open questions or relevant planning notes.
Why use it?
It helps an agent recover the project’s working context after a break without relying only on an old conversation.

Skill for Claude CodeCodex

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

Made for: Claude Code, Codex.

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-pickup

README.md
[![agentmods](https://agentmods.dev/badge/skills/febradc-github/turnstile/turnstile-pickup.svg)](https://agentmods.dev/skills/febradc-github/turnstile/turnstile-pickup)
Your own site
<a href="https://agentmods.dev/skills/febradc-github/turnstile/turnstile-pickup"><img src="https://agentmods.dev/badge/skills/febradc-github/turnstile/turnstile-pickup.svg" alt="Measured on agentmods" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 739 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 $0.00086 $0.00739
Opus 5 $0.00043 $0.00369
Sonnet 5 $0.00017 $0.00148
Haiku 4.5 $0.00009 $0.00074

Measured 4d ago against content hash 65fe12ae243d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

turnstile-pickup 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.

skills/turnstile-pickup/SKILL.md · 29 lines

How it starts

The opening of the file, as written. The whole thing — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pickup

Process

  1. Read the current board -- turnstile/sprint.yml (a sprint or a mode: flow board), or (legacy boards) the root turnstile/sprint-*.yml with sprint.status: active. If none exists, tell the user and suggest /turnstile:sprint-plan (or /turnstile:next in cadence: flow).
  2. Find the in_progress item. For it, report -- in this order:
    • What you were about to do: the most actionable open thread -- the last notes entry (work passes, debug notes, review FAIL reasons), plus which acceptance criteria look unmet against the current diff (git status / git diff for uncommitted work-in-progress).
    • What was blocking: anything in the notes or the item note that reads as a blocker or open question -- surface it even if stale.
    • Where it stands: id, title, status, work-pass count, and its criteria source (spec SP-<n>, plan PL-<n>, or inline).
    • Context links: the item note, its design/plan, and vault notes related to its topic (search_notes) -- especially adr-*/AR-* notes and anything the last session's curator dispatches recorded.
  3. An item with status: review and no in_progress item: an interrupted review session -- point at /turnstile:review <id> to resume it.
  4. No in-progress item, but parked item(s) exist: offer to un-park the most recently parked one (highest parked_at), reading its ## Resume section aloud first -- that is the context being restored. On confirmation: set its status back to in_progress, remove parked_at, and append unparked to its notes; the ## Resume section stays in the item note as history. Declined: list the parked items and continue to step 5.
  5. No in-progress and nothing parked (or un-park declined): say so and point at the natural next move -- the board's todo items (/turnstile:work <id>), or /turnstile:sprint-plan / /turnstile:next when the board is empty.
  6. Finish with the single next command to run.

Read the full file on GitHub · 29 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. 4d ago First seen · 29 lines · 86 tokens per session scan A 65fe12ae243d

Subscribe to this mod's changes

turnstile-pickup is a skill published in the GitHub repository febradc-github/turnstile (1 stars, last pushed 1mo ago), licensed MIT. It adds 86 tokens to every session and 739 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

specify-meta

Scaffold, status-check, and manage specification directories. Use when creating a new spec, reading spec status, transitioning between phases, or logging decisions on a spec in .start/specs/.

rsmdt/the-startup · 42 tokens

feature-prioritization

RICE, MoSCoW, Kano, and value-effort prioritization frameworks with scoring methodologies and decision documentation. Use when prioritizing features, evaluating competing initiatives, creating roadmaps, or making build vs defer decisions.

rsmdt/the-startup · 51 tokens

user-story-generator

Transforms requirements into user stories with Given/When/Then acceptance criteria ready for sprint planning and Jira. Use when user needs to write user stories, create Jira tickets, define acceptance criteria, or says "user stories", "acceptance criteria", "sprint backlog", "Jira tickets", "as a user I want"…

lenar-amirov/product-pipeline-public · 76 tokens

spec

Turn a wireframe and everything already agreed into a written spec in traditional agile shape — an initiative broken into epics, epics into user stories with acceptance criteria, and themes as the labels that span them — presented as an interactive drill-down tree the user prunes, edits and annotates in the browser…

Cavalry-Collective/visual-stack · 115 tokens

user-story-map

Build an interactive, drag-and-drop user story map so the user can re-slice work across release phases. Use when the user wants a story map, a phased roadmap, release slicing, a backbone/activities journey map, or to decide "which stories go in which phase" and move them around.

Cavalry-Collective/visual-stack · 65 tokens

ambiguity-resolver

Structures a brief HANDED DOWN by a stakeholder (boss, exec, another team) into a one-page problem statement with scope boundaries and a named decision owner. Use when the PM says "мне спустили задачу", "I've been asked to look into Y", "руководство хочет X", "CEO попросил разобраться" — a request the PM didn't…

lenar-amirov/product-pipeline-public · 98 tokens