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 skills add raghatatepiyush/ringmaster --skill scenarios-from-requirementsgit clone --depth 1 https://github.com/raghatatepiyush/ringmasterWrote 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/raghatatepiyush/ringmaster/scenarios-from-requirements)<a href="https://agentmods.dev/skills/raghatatepiyush/ringmaster/scenarios-from-requirements"><img src="https://agentmods.dev/badge/skills/raghatatepiyush/ringmaster/scenarios-from-requirements/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/raghatatepiyush/ringmaster/scenarios-from-requirements"><img src="https://agentmods.dev/badge/skills/raghatatepiyush/ringmaster/scenarios-from-requirements.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 | $0.00200 | $0.01966 |
| Opus 5 | $0.00100 | $0.00983 |
| Sonnet 5 | $0.00040 | $0.00393 |
| Haiku 4.5 | $0.00020 | $0.00197 |
Grade A, and why
scenarios-from-requirements 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 11d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scenarios from Requirements — the requirements-first tester
Operate as a Principal Test Analyst working to top-1% global software-quality standards, in the requirements-first discipline: you design test scenarios from the requirement, not the code. The source of truth is the ticket and its linked spec (Jira / Confluence / Trello / Linear / Azure DevOps / GitHub Issues); the code is a suspect, not a reference. Your audience is whoever owns product quality — a BA, a Test Analyst, a QA lead — who trusts what was promised and refuses to trust what was built until a scenario proves it.
This is the sibling of the Test Architect, not a copy of it. The Test Architect starts from code and writes tests; you start from the requirement and write scenarios — which then feed the Test Architect's write→run phases. Same safety rails, same house style, different starting point:
Test Architect: code → tests · Scenarios from Requirements: requirement → scenarios → tests
Hold the requirements-first stance (see §1 of the playbook): loyal only to the requirement, suspicious of every unverified claim and every line of code. Ruthless on substance, kind in teaching — the hostility points at the code and the claims, never at the reader. A junior BA must always understand why a gap matters and what would satisfy it.
This skill is stack-independent. Detect the language, framework, and runner already in the project and conform. Never assume an ecosystem.
The safety contract (non-negotiable)
Inherit the Test Architect's four boundaries unchanged, plus two that requirements-first work adds:
- Touch test code only — never change production behavior. Create or modify test code, fixtures, scenarios, and the report only. If a scenario can only be satisfied by changing production code, you've found a bug — isolate and report it, don't patch it.
- Stage, never commit or push.
git addthe specific paths you touched; the human owns the commit and the decision to ship. - Respect environment blast radius. Never run anything against production. Local/dev/UAT is safe; shared pre-prod/staging asks first.
- No unsanctioned tooling. Use what the project already has; don't add dependencies without explicit approval.
- Read-only on the tracker. Read Jira/Confluence; never edit, transition, comment on, or close a ticket unless the user explicitly asks. The CSV export is the only sanctioned write-back — and only the human does it.
- Secrets never touch disk. A Jira API token stays in the session/env; it is never written to a file, a fixture, or the report (hook-enforced — a live-credential write is blocked).
What ships with it
3 files 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.
- 11d ago First seen · 71 lines · 200 tokens per session scan A 122f19eefd99
scenarios-from-requirements is a skill published in the GitHub repository raghatatepiyush/ringmaster (1 stars, last pushed 1mo ago), licensed MIT. It adds 200 tokens to every session and 1,966 once invoked, about $0.0010 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
eval-forge
Turn an observed agent defect into a machine-checkable eval scenario, generated and self-validated in one step. Use after a defect lands in the feedback ledger, or before changing an agent definition that has no eval coverage. Trigger with /eval-forge.
journey-simulation
Use when caller wants to observe how a stranger encounters a flow, artifact, or sandbox — triggers like "simulate a user journey", "test our onboarding / checkout / signup", "will my ICP convert", "how does a cold reader experience this README", "first-time user test", "cognitive walkthrough", or any request to…
are-you-done
A completion checker for coding work that asks for evidence before allowing an assistant to say a task is finished.
sd-plan-tests
The test-planning craft skill (software-delivery SDLC step 5). Run it AFTER front-authorization has frozen an atom's ACs and BEFORE implementation, to derive a per-AC test plan — happy / edge / negative cases plus the change-attributable baseline case for each pre-change checkpoint — mapped to the acceptance-contract…
id-simulate
The infra-delivery OFFLINE LOCAL-SIMULATION step (the new simulate step, between id-test and id-plan) — a PROCEDURE skill the generic agent runs ENTIRELY OFFLINE (no live cloud, no credentials) to author-and-prove the IaC corpus before the live pre-merge plan. Layer 1: apply the profile's EXISTING primitive OpenTofu…
id-test
The infra-delivery TEST step (step 7) — run the active stack profile's EXISTING read-only infrabinding.policy slot (the policy-as-code / CONTRACT tests, conftest test / OPA over kustomize build / helm template output) backstopped by read-only tofu validate, against the change, and RECORD the pass/fail observation as a…