Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Hulupeep/Specflownpx agentmods add skills/hulupeep/specflow/specflow-loop-selectorWrote 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/hulupeep/specflow/specflow-loop-selector)<a href="https://agentmods.dev/skills/hulupeep/specflow/specflow-loop-selector"><img src="https://agentmods.dev/badge/skills/hulupeep/specflow/specflow-loop-selector/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hulupeep/specflow/specflow-loop-selector"><img src="https://agentmods.dev/badge/skills/hulupeep/specflow/specflow-loop-selector.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00065 | $0.04084 |
| Opus 5.5 | $0.00026 | $0.01634 |
| Sonnet 5.5 | $0.00013 | $0.00817 |
| Haiku 4.5 | $0.00006 | $0.00408 |
Grade A, and why
specflow-loop-selector 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 today.
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 — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Specflow Loop Selector
Choose The Work Weight
Choose the lightest level that covers the actual risk before selecting a loop. Inspect the affected behaviour and interfaces; file count, issue labels and a small diff do not establish low risk. Reuse current tickets and evidence. State one short decision in the existing task/issue or response: weight, reason, required checks, simulation needed or not, loop needed or not. Do not create a triage document, ticket, run contract or provider call just to make this decision. Include the observable outcome and key uncertainty in that same brief decision; reuse the existing goal and acceptance rather than creating another artifact. For a research-agent handoff with selected issues, start at the first missing contract/check, not discovery. Reuse cited research; return a concrete evidenced contradiction to the researcher instead of silently selecting a different idea. Bind handoffs to a role and durable task/contract identity, not a bot brand or chat session. A replacement reads the current authorised role brief, assignment and prior evidence; it reconciles existing work before starting a new job.
| Weight | Typical ask | Parts to invoke |
|---|---|---|
| Tweak | Copy, CSS, a display-only component; deck hint or compact cards | No Specflow ceremony. Relevant unit tests, lint and an emulator screenshot for changed UI (browser equivalent for web). |
| Bug | Stale flick-down, ghost-click tap | Capture a failing regression test before the fix, then pass it and applicable contract tests. A short issue is enough; add a journey when the failure crosses UI/backend boundaries. |
| UI feature, no schema change | Reorder, quick add, full deck using established behaviour | Short ticket with Gherkin, failure cases and data-testid selectors; contract tests and an executed emulator/browser journey. Simulate only for a new or changed gesture/mental model, or an already-required gate. |
| Schema or RPC change | Table, constraint, RLS, trigger or RPC contract change | Full ticket; Gate C with migration replay, rollback and pgTAP; CI migration-replay. These checks are mandatory for the applicable database change, even if the diff is tiny. |
| New concept / behaviour change | Detours, pause reasons, changing what “hold” means | Simulate personas and edge routes before building; run a kill check, then implement with the applicable UI/database verification. |
| Multi-slice epic | A Live Stax build spanning dependent slices | Coordinate waves and dependencies, run slice journey gates, then Gate D on the merged result. Keep each slice’s applicable checks. |
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.
- today Changed · +60 lines f105e916c55e
- 14d ago Changed 1106058ec9b8
- 17d ago Changed · +92 lines · -41 tokens per session 5dbe53b8d651
- 1mo ago Changed · +11 lines 165749460101
- 1mo ago First seen · 178 lines · 106 tokens per session scan A cc047900b0a3
specflow-loop-selector is a skill published in the GitHub repository Hulupeep/Specflow (25 stars, last pushed today), licensed MIT. It adds 65 tokens to every session and 4,084 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
devsecops-complete-audit
Audit professionnel complet d'un projet logiciel couvrant architecture, code mort, dette technique, dépendances, API, authentification, autorisation, sécurité applicative, CI/CD, performance, production et validation finale.
architecture-paradigm-pipeline
Applies pipes-and-filters for sequential data transformations. Use when data flows through discrete stages like ETL, streaming analytics, or CI/CD pipelines.
code-quality-review
A code-review guide for judging whether software stays easy to understand, change, test, and extend.
github-actions-workflow
Scaffolds or audits a GitHub Actions CI/CD workflow for a project. Covers job structure, caching, secrets handling, concurrency groups, environment gates, and reusable workflows via workflowcall. Invoked when the user asks to set up CI, add a GitHub Actions workflow, improve pipeline performance, or share workflow…
template-guide
Navigate template conventions, audit compliance, and guide upgrades for ai-project-template repos.
merge-to-main
Babysit a PR through CI — create, monitor, fix failures, merge when green.