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/andreaswasita/copilot-agents-dojonpx agentmods add skills/andreaswasita/copilot-agents-dojo/derive-nfr-from-driverWrote 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/andreaswasita/copilot-agents-dojo/derive-nfr-from-driver)<a href="https://agentmods.dev/skills/andreaswasita/copilot-agents-dojo/derive-nfr-from-driver"><img src="https://agentmods.dev/badge/skills/andreaswasita/copilot-agents-dojo/derive-nfr-from-driver/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/andreaswasita/copilot-agents-dojo/derive-nfr-from-driver"><img src="https://agentmods.dev/badge/skills/andreaswasita/copilot-agents-dojo/derive-nfr-from-driver.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00018 | $0.01326 |
| Opus 5 | $0.00009 | $0.00663 |
| Sonnet 5 | $0.00004 | $0.00265 |
| Haiku 4.5 | $0.00002 | $0.00133 |
Grade A, and why
derive-nfr-from-driver 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 12d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Derive NFR From Driver
Turns a ratified business driver (BR) — and the functional requirements (FRs) derived from it — into measurable Non-Functional Requirements with verified parentage. This skill does NOT elicit drivers and does NOT invent FRs; it derives NFRs against parents that already exist on disk.
When to Use
- A
BR-*and at least oneFR-*exist for the engagement and need performance, availability, scalability, or accessibility targets before Phase D begins. - The architect is about to design components and needs SLO-shaped inputs, not adjectives.
- A reviewer asks "what does fast mean?" — derive an NFR with a numeric target instead of arguing prose.
- NOT when the driver itself is unratified — go to
requirements-elicitationfirst.
Prerequisites
requirements/<engagement>/BR/contains at least one ratifiedBR-*artifact (ratified_byis non-empty).requirements/<engagement>/FR/contains the FR(s) this NFR will constrain.spec/artifact-schema.mdis the contract for frontmatter fields.
If a prerequisite is missing the skill must stop and report — never emit an NFR pointing at a non-existent or unratified parent.
How to Run
# 1. Confirm the parent exists and is ratified
bash scripts/verify-traceability.sh requirements/<engagement>
# 2. Create the NFR file (filename MUST equal {id}.md)
# Then run the gate again to prove the new link resolves
bash scripts/verify-traceability.sh requirements/<engagement>
Quick Reference
| Action | Tool | Notes |
|---|---|---|
| Read parent BR/FR | view |
Get the exact id values. |
| List existing NFRs | glob requirements/<engagement>/NFR/*.md |
Pick the next free NFR-NNN. |
| Write NFR | create |
Frontmatter per spec/artifact-schema.md. |
| Verify lineage | bash scripts/verify-traceability.sh |
Must pass before commit. |
The frontmatter the agent emits:
---
id: NFR-007
layer: NFR
title: Classification latency under load
parent_ids: [BR-001, FR-002]
owner: [email protected]
measurable: true
ratified_by: ""
target: "p95 < 2s on 3G, p99 < 4s"
derivation_skill: derive-nfr-from-driver
tags: [latency, classification]
---
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.
- 12d ago First seen · 144 lines · 18 tokens per session scan A a9da8cd60301
derive-nfr-from-driver is a skill published in the GitHub repository andreaswasita/copilot-agents-dojo (53 stars, last pushed 4d ago), licensed MIT. It adds 18 tokens to every session and 1,326 once invoked, about $0.0001 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
decision-ledger
A session record for tracking unresolved decisions and drafting them into `.governance/claims/` when they are settled. It preserves both the decision and the reason behind it.
governance-bootstrap
A guided checklist for creating a project's governance system from scratch when no governance exists.
session-grounding
A session-start procedure for checking the current facts, scope, and work track in a governed project before taking action.
truth-first
A set of rules for writing technical conclusions and performing irreversible or state-changing operations. It requires evidence tied to file and line locations and restricts unsupported claims.
todos
This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…
writing-workflow-skills
Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.