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-refinenpx skills add febradc-github/turnstile --skill turnstile-refinegit 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-refine)<a href="https://agentmods.dev/skills/febradc-github/turnstile/turnstile-refine"><img src="https://agentmods.dev/badge/skills/febradc-github/turnstile/turnstile-refine.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 | $0.00049 | $0.01466 |
| Opus 5 | $0.00024 | $0.00733 |
| Sonnet 5 | $0.00010 | $0.00293 |
| Haiku 4.5 | $0.00005 | $0.00147 |
Grade A, and why
turnstile-refine scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refine
Process
- Search the vault (brain, decisions, architecture, item notes -- search_notes indexes all of them) for notes related to the idea's topic ($ARGUMENTS). Surface anything relevant, including conflicts, before continuing.
- Compute the next ticket ID: scan
turnstile/backlog.yml,turnstile/sprint.yml,turnstile/sprints/*.yml, and any legacyturnstile/sprint-*.ymlfor existingC-<N>ids; the new id isC-<max+1>, orC-1if none exist. - Run a one-question-at-a-time dialogue to establish:
- A clear title and one-paragraph problem description.
- Architecture fit: where this sits in the existing system. Read related
AR-*andadr-*notes first; ask about integration points and affected components. If the work contradicts an existing ADR, surface the conflict explicitly -- the user decides whether the old decision is superseded, and brain-curator records the superseding ADR. - Design decisions: the approach, and any choice between real alternatives this work forces. Close these gaps now -- a ticket that reaches
/turnstile:workwith an open design question was refined too early. - Non-empty
acceptance_criteria(concrete, checkable statements). - A
pointsestimate (any positive integer the user agrees to). assignee:claudeorhuman(defaultclaude). While talking, assess scale: multiple independent deliverables or an estimate above 8 points meanstype: epic, with acceptance criteria at the outcome level; the pieces get their own criteria later via/turnstile:breakdown.
- Check whether the target artifact already exists (
<n>from<id>=C-<n>):turnstile/designs/DS-<n>.mdin full profile,turnstile/plans/PL-<n>.mdin solo (check both -- the profile may have switched), or a legacyturnstile/designs/<id>*.md. An existing file with no matching board entry is an abandoned draft from a prior refine session: warn the user and ask whether to overwrite it or useid+1for a fresh draft (re-checking the new id for a collision too). Never overwrite silently. Then writeturnstile/designs/DS-<n>.md(full) orturnstile/plans/PL-<n>.md(solo leaf; epics always get a design doc) per the templates reference. - Present the design doc (or plan) content and ask for explicit approval. Revise and re-present until approved; do not proceed without it. In solo this is the item's only pre-work gate -- the plan's criteria are what /turnstile:review will check.
- Once approved: append the item to
turnstile/backlog.yml(creating it withitems: []first if missing) and write the item note (EP-<n>for an epic,US-<n>otherwise), both per the templates reference. Solo leaf items enter withstatus: ready; full-profile items and epics withstatus: idea. Write the design doc (or plan) and item note in the same pass -- they link each other. Before finishing, confirm every [[wikilink]] added resolves (list_unresolved_links); an unresolved link is a click-trap that mints a stray note. - Capture (per the capture config): in
gatesmode (default), dispatchbrain-curatoronce after the approval, with bounded input -- the approved design or plan artifact (DS-<n>/PL-<n>) -- to link it into the vault and record any ADR-worthy choice it contains (a decision between real alternatives with lasting consequences); tell the curator which item notes are affected. Inopportunisticmode, dispatch only if the dialogue surfaced something worth remembering (a decision record, newly established system shape). - Tell the user what is next: full profile -- the design is recorded and
/turnstile:spec <id>is next; solo -- the plan is approved and the item isreadyfor/turnstile:sprint-plan. For an epic (either profile), invoketurnstile-breakdownwith the epic's id (its own approval gate governs the split).
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 · 43 lines · 49 tokens per session scan A 7346c3221264
turnstile-refine is a skill published in the GitHub repository febradc-github/turnstile (1 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 1,466 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
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…