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 telus-labs/stagecraft --skill spec-authoringgit clone --depth 1 https://github.com/telus-labs/stagecraftWrote 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/telus-labs/stagecraft/spec-authoring)<a href="https://agentmods.dev/skills/telus-labs/stagecraft/spec-authoring"><img src="https://agentmods.dev/badge/skills/telus-labs/stagecraft/spec-authoring.svg" alt="Measured on agentmods" 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 | $0.00068 | $0.01396 |
| Opus 5 | $0.00034 | $0.00698 |
| Sonnet 5 | $0.00014 | $0.00279 |
| Haiku 4.5 | $0.00007 | $0.00140 |
Grade A, and why
spec-authoring 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 7d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec authoring — closed-loop AC → Scenario → Test
The brief is in prose. Tests are in code. The gap between them is where
regression hides. The executable spec (Gherkin) is the bridge — every
brief AC becomes one Scenario, every Scenario must have at least one test.
devteam spec verify catches drift; the stage-03b gate records the mapping.
When to use
You're authoring stage-03b. The orchestrator has just finished clarification
and your task is to translate the brief's AC-N lines into Gherkin scenarios
in pipeline/spec.feature. Tracks: full, quick.
Phase 1 — Load context
Read in order:
pipeline/brief.md— extract everyAC-Nline. These are your inputs.pipeline/clarification-log.md(if present) — answers may have refined ACs.pipeline/design-spec.md(if present) — design hints the Given/When/Then.
Confirm the brief has at least one AC-N line. If it doesn't, stop — go back
to PM and tighten the brief first. Don't try to invent ACs from prose.
Phase 2 — Scaffold
devteam spec generate
This writes pipeline/spec.feature with one @AC-N + Scenario: block per
AC found in brief.md. The Given/When/Then lines are TODO placeholders. The
scaffold makes it harder to forget an AC than to remember it.
If the file already exists, the command refuses to overwrite. Edit by hand
or pass --force (rare — usually you've drifted and want verify to tell
you exactly what's off).
Phase 3 — Fill in steps
For each scenario:
- Given — the precondition. State of the system before the user acts. Concrete: "Given a user with email [email protected] exists" — NOT "Given a user".
- When — the action. The thing that triggers the behaviour. One verb, one object: "When the user submits the sign-in form" — NOT "When the user signs in successfully" (don't smuggle the outcome into the action).
- Then — the observable outcome. From the outside of the system. "Then a session cookie is set with HttpOnly + SameSite=Strict" — NOT "Then the internal SessionService is called" (internals aren't observable).
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.
- 7d ago First seen · 131 lines · 68 tokens per session scan A 2c9dcfa5430d
spec-authoring is a skill published in the GitHub repository telus-labs/stagecraft (6 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 1,396 once invoked, about $0.0003 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
intuitive-tests
Use this skill whenever the user asks about unit test best practices, test organization, flat test suites, redundant tests, test refactors, pytest/JUnit/Jest/xUnit layout, test taxonomy, flaky tests, coverage quality, fixtures, mocks, parametrization, pruning existing UTs, or "which tests are worth keeping." It…
verify
Run the HUMHUM quality gates that are actually touched by the current diff — frontend typecheck + vitest, and Rust fmt/clippy/test — mirroring CI. Use before marking work done, opening a PR, or when asked to "verify", "check", or "run the gates".
test-generation
Generate comprehensive tests for code including unit tests, integration tests, and edge case coverage. Analyzes code to identify testable units and generates tests matching the project's testing framework and conventions.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
build-and-test
How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.
writing-tests
Write unit tests, component tests, and integration tests for AiderDesk using Vitest and React Testing Library. Use when creating new tests, adding test coverage, configuring mocks, setting up test files, or debugging failing tests.