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-breakdownnpx skills add febradc-github/turnstile --skill turnstile-breakdowngit 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-breakdown)<a href="https://agentmods.dev/skills/febradc-github/turnstile/turnstile-breakdown"><img src="https://agentmods.dev/badge/skills/febradc-github/turnstile/turnstile-breakdown.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 | $0.00055 | $0.01096 |
| Opus 5 | $0.00028 | $0.00548 |
| Sonnet 5 | $0.00011 | $0.00219 |
| Haiku 4.5 | $0.00006 | $0.00110 |
Grade A, and why
turnstile-breakdown scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Breakdown
Process
- Look up
<id>(from$ARGUMENTS) inturnstile/backlog.yml.- Found in a sprint file instead: refuse; sprint items are already committed scope.
- Not found anywhere: refuse; suggest
/turnstile:refine <idea>to create it first. type: task: refuse; tasks are leaves. A too-big task means the parent story's breakdown is wrong -- revisit that instead.
- Decide the child type:
epicparent ->storychildren;storyparent (explicit or absenttype) ->taskchildren. - Search the vault (brain, decisions, architecture, item notes) for notes related to the item's topic. Surface anything relevant, including conflicts.
- Read the item's design doc --
turnstile/designs/DS-<n>.md(<n>from<id>=C-<n>), falling back to legacy names (turnstile/designs/<id>-*-design.md,turnstile/designs/<id>.md) -- plus the parent epic's design when breaking a story with aparent. No design doc: refuse and direct the user to/turnstile:refine-- breakdown decomposes an approved design, it does not invent one. - Draft 2-8 children. Each: clear title, one-paragraph description, non-empty
acceptance_criteria, apointsestimate, anassignee(inherit the parent's unless told otherwise). Children must partition the parent's scope: together they cover its acceptance criteria, no two overlap. If the scope honestly fits in one child, say so and recommend skipping breakdown. - Present the full proposal (every child, every field) for explicit approval. Revise and re-present on requested changes. Write nothing until approved.
- Once approved, per the templates reference:
- Mint child ids: scan
turnstile/backlog.yml,turnstile/sprint.yml,turnstile/sprints/*.yml(plus legacyturnstile/sprint-*.yml) for existingC-<N>ids; children getC-<max+1>,C-<max+2>, ... For each id, check noDS-<n>design (or legacy equivalent) already exists -- an abandoned draft may hold it; if so, warn the user and skip to the next free id. Never overwrite silently. - Write each child's design doc and item note as one pass per child -- they cross-link.
- Update the parent's item note: add each child under a
Children:list, add them torelated, setupdatedto today. (A legacy parent with no item note: create one now in its type's folder.) - Append each child to
turnstile/backlog.yml, and update the parent there: it is now a container -- if itsstatuswasready, set it back toidea(containers never enter sprints), and setupdatedto today. - Before finishing, confirm every [[wikilink]] added resolves (list_unresolved_links); an unresolved link is a click-trap that mints a stray note.
- Mint child ids: scan
- If the dialogue surfaced something worth remembering (a scoping decision, a rejected split and why), dispatch
brain-curatorwith a short description. - Tell the user the breakdown is recorded and each child needs
/turnstile:spec <child-id>to becomeready.
What ships with it
1 file 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.
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.
- 4d ago First seen · 44 lines · 55 tokens per session scan A b07390e5331c
turnstile-breakdown is a skill published in the GitHub repository febradc-github/turnstile (1 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 1,096 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.
Other skills, from other repositories
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…
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…
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…
financial-statement-analysis
Reads a set of financial statements and establishes what changed and why — fluctuation analysis against prior period and against budget, profitability, liquidity, solvency and efficiency ratios, benchmarking, and the non-GAAP measures presented alongside them. Use this to interpret results, review a counterparty's or…
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…
estimating-and-contingency
Produces a cost or effort estimate someone can defend — decomposing the work, choosing between analogous, parametric and bottom-up methods, documenting the basis and its assumptions, expressing confidence as a range, and sizing contingency and management reserve separately. Use this to build an estimate, challenge one…