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.
npx agentmods add skills/febradc-github/turnstile/turnstile-worknpx skills add febradc-github/turnstile --skill turnstile-workgit clone --depth 1 https://github.com/febradc-github/turnstileWrote 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.
[](https://agentmods.dev/skills/febradc-github/turnstile/turnstile-work)<a href="https://agentmods.dev/skills/febradc-github/turnstile/turnstile-work"><img src="https://agentmods.dev/badge/skills/febradc-github/turnstile/turnstile-work.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00042 | $0.01433 |
| Opus 5 | $0.00021 | $0.00717 |
| Sonnet 5 | $0.00008 | $0.00287 |
| Haiku 4.5 | $0.00004 | $0.00143 |
Grade A, and why
turnstile-work scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Work
Process
- Look up
<id>(from$ARGUMENTS) in the current board --turnstile/sprint.yml(a sprint or amode: flowboard), or (legacy) the rootturnstile/sprint-<N>.ymlwithsprint.status: active. No active board, or id not on it: tell the user and suggest/turnstile:sprint-plan--/turnstile:nextincadence: flow-- (or/turnstile:quickfor small work). assignee: human: refuse and point the user at the item.statusnottodoorin_progress(never planned in, mid-review, orparked): refuse and redirect to the correct step -- for aparkeditem,/turnstile:pickupun-parks it with its resume context.- Another item already
in_progress: refuse; the user finishes it via/turnstile:reviewfirst. - Search the vault for notes related to this ticket's topic. Surface anything relevant, including conflicts, before writing code. Pay particular attention to
adr-*andAR-*notes touching this area: the implementation must not silently contradict a recorded decision. - Read the ticket's spec --
turnstile/specs/SP-<n>.md(<n>from<id>=C-<n>), falling back to legacy names (turnstile/specs/<id>-*-spec.md,turnstile/specs/<id>.md). No spec file means a quick-lane item: its criteria live in the item note's "## Acceptance criteria" section. If the item has aparent, also read the parent chain's design docs (DS-<parent n>, or legacy names) -- the umbrella rationale often settles questions the leaf spec doesn't repeat. - Set
status: in_progressif it wastodo-- before writing any code, so an interrupted session still leaves the board accurate. - If any acceptance criterion is UI-facing, defer to
frontend-design(if installed) for that portion. - Ask the user:
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.
- 3d ago First seen · 49 lines · 42 tokens per session scan A 5f821a74ae3a
turnstile-work is a skill published in the GitHub repository febradc-github/turnstile (1 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 1,433 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.
Other skills, from other repositories
specify-incremental
Decompose a single-feature specification into a linear, phase-by-phase implementation plan. Use this for medium-complexity work — single feature, one or two components — where transparent human-in-the-loop phase review is preferred over factory automation.
execute
Dispatch and execute implementation plans with TDD and checkpoints. Use when plan is ready. Parallel by default for independent tasks.
tdd
Strict test-driven development for behavior changes. Requires verified RED before production code, minimal GREEN, and refactor only after passing tests.
pdlc-feature
全自动 PDLC 新功能开发（串联 PRD→设计→TDD→实现→评审→发布）.
the-loop
The operating model for delivering product work items end-to-end with an agent harness. Use whenever working a ticket/issue under the-loop — to write the spec chain (requirements/design/testing-plan/tasks), execute the task DAG, verify against the testing plan, self/critic-review, escalate, present evidence, and…
pdlc-tdd
Skill "pdlc-tdd" from kanfu-panda/pdlc-skills, covering tdd 测试先行, pdlc 前置检查（必须执行，不可跳过）, 工作流程 and 要求.