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 FortiumPartners/ensemble --skill ensemble-validate-requirementsgit clone --depth 1 https://github.com/FortiumPartners/ensembleWrote 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/fortiumpartners/ensemble/ensemble-validate-requirements)<a href="https://agentmods.dev/skills/fortiumpartners/ensemble/ensemble-validate-requirements"><img src="https://agentmods.dev/badge/skills/fortiumpartners/ensemble/ensemble-validate-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/fortiumpartners/ensemble/ensemble-validate-requirements"><img src="https://agentmods.dev/badge/skills/fortiumpartners/ensemble/ensemble-validate-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 | $0.00043 | $0.01844 |
| Opus 5 | $0.00022 | $0.00922 |
| Sonnet 5 | $0.00009 | $0.00369 |
| Haiku 4.5 | $0.00004 | $0.00184 |
Grade A, and why
ensemble-validate-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 9d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ensemble Command: /ensemble:validate-requirements
This Codex skill mirrors the Ensemble slash command /ensemble:validate-requirements.
Follow the workflow below, adapt to the current repository, and keep outputs structured.
Parse a PRD for all REQ-NNN and AC-NNN-M IDs, parse a TRD for all [satisfies] and [verifies] annotations, and report coverage gaps, orphaned annotations, and missing -TEST task pairs. CI-friendly: exits non-zero on errors, zero on warnings-only.
Workflow
Phase 1: Document Parsing
1. Input Validation Verify that both required arguments are provided and that both files exist on disk.
If $ARGUMENTS does not contain two tokens: print 'ERROR: Usage: /ensemble:validate-requirements ' and EXIT with code 1. Resolve PRD_PATH from the first argument. If file does not exist: print 'ERROR: PRD file not found: <PRD_PATH>' and EXIT with code 1. Resolve TRD_PATH from the second argument. If file does not exist: print 'ERROR: TRD file not found: <TRD_PATH>' and EXIT with code 1.
2. PRD Parsing Parse PRD document for all traceability IDs. Extract all REQ-NNN IDs from H3 headings matching '### REQ-NNN:' pattern. Extract all AC-NNN-M IDs from bullet items matching '- AC-NNN-M:' pattern. Build PRD_REQUIREMENTS map: REQ-NNN -> {description, acs: [AC-NNN-M, ...]} Build PRD_AC_SET: flat set of all AC-NNN-M IDs. Note: IDs must match exactly (REQ-001, not REQ-1 or req-001). IDs that do not match the pattern ### REQ-NNN: are silently skipped. If requirements appear uncovered or orphaned unexpectedly, verify the ID format matches exactly in both PRD and TRD. If PRD has no REQ-NNN IDs: print 'NOTE: PRD has no REQ-NNN IDs — this PRD does not support traceability analysis. If the TRD has [satisfies REQ-NNN] annotations, they will all appear as orphaned errors. Either add REQ-NNN IDs to the PRD or remove [satisfies] annotations from the TRD. EXIT with code 0 (no analysis performed).'
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.
- 9d ago First seen · 138 lines · 43 tokens per session scan A 09c798ce19d0
ensemble-validate-requirements is a skill published in the GitHub repository FortiumPartners/ensemble (12 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 1,844 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 2026-08-30.
Other skills, from other repositories
bmad-qa-generate-e2e-tests
Generate end to end automated tests for existing features. Use when the user says "create qa automated tests for [feature]".
joycraft-implement
Execute atomic specs with TDD — read spec, write failing tests, implement until green, wrap up and continue the queue.
joycraft-implement-level5
Invoked by tune's roadmap or the human opting into Level 5 — set up the autofix loop, holdout scenario testing, and scenario evolution from specs.
responsive-audit
Responsive audit: test pages at 375/768/1024px breakpoints via Playwright. Checks overflow, tap targets, sidebar collapse, text reflow, WCAG 1.4.4 zoom.
test-audit
Static test-suite quality audit - coverage from lcov/Istanbul/Cobertura/go/tarpaulin reports, pyramid shape (unit/integration/e2e ratio), anti-patterns (.only leaks, skipped tests, no-assertion tests, hardcoded sleeps). Stack-aware across 11 supported stacks.
cli-forge-resilience
Generate a production-parity resilience blueprint: test battery, troubleshooting runbook, agent-ready operations pack, failure-injection plan, and incident blackbox templates. Uses biological and physical reasoning — genome/contracts, membranes/boundary conditions, homeostasis/health checks, immune system/negative…