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 intent-driven-dev/intent-driven-template --skill acceptance-test-authoringgit clone --depth 1 https://github.com/intent-driven-dev/intent-driven-templateWrote 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/intent-driven-dev/intent-driven-template/acceptance-test-authoring)<a href="https://agentmods.dev/skills/intent-driven-dev/intent-driven-template/acceptance-test-authoring"><img src="https://agentmods.dev/badge/skills/intent-driven-dev/intent-driven-template/acceptance-test-authoring/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/intent-driven-dev/intent-driven-template/acceptance-test-authoring"><img src="https://agentmods.dev/badge/skills/intent-driven-dev/intent-driven-template/acceptance-test-authoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 20 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
- medium MCP Rug Pull · line 98 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00051 | $0.01793 |
| Opus 5.5 | $0.00020 | $0.00717 |
| Sonnet 5.5 | $0.00010 | $0.00359 |
| Haiku 4.5 | $0.00005 | $0.00179 |
Grade A, and why
acceptance-test-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 1mo 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Acceptance Test Authoring
When spec-as-source is active, the acceptance suite executes the Gherkin specs that live under openspec/ against the running application. Specs are Markdown files named spec.md: Markdown headings carry the capability, requirement, and scenario structure, while column-0 gherkin fences contain only Given/When/Then steps. The runner extracts them into real .feature files on every run, synthesizing Feature:/Rule:/Scenario: from the headings.
This format is opt-in. Loading this skill without spec-as-source does not override the configured OpenSpec schema templates.
Everything in this file is stack-agnostic. Tool-specific filenames, dependencies, commands, and examples live in the stack packs.
Choosing The Stack
The project's acceptance stack is declared as stack: in openspec/config.yaml:
schema: intent-driven
stack: javascript # javascript | python
Resolve it in this order:
- Use
stack:inopenspec/config.yaml. - If absent and
acceptance-tests/already exists, infer it from contents:cucumber.cjsmeansjavascript,behave.inimeanspython; offer to record it. - Otherwise ask. Never guess silently, and never scaffold a runner without a recorded value.
When spec-as-source is active, adding stack: is a specs-zone edit under openspec/; follow that skill's mandatory BDD zone rules before editing it.
Reference Files
| Stack | Pack | Runner |
|---|---|---|
javascript |
references/javascript/SETUP.md | cucumber-js |
python |
references/python/SETUP.md | behave 1.2.7+ |
Each pack has a Files to copy table naming every destination filename and why it is load-bearing. Copy those files verbatim; they are the canonical runner.
Three files sit at the references/ root because they are shared by both stacks:
| File | Role |
|---|---|
| EXTRACTION.md | Normative contract for spec.md to .feature extraction |
| COMPOSITION.md | Normative contract for which scenarios run |
| gherkin-lintrc.json | Shared lint configuration copied to acceptance-tests/.gherkin-lintrc |
What ships with it
13 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.
- references/COMPOSITION.md 5.1 KB
- references/EXTRACTION.md 5.9 KB
- references/gherkin-lintrc.json 1.3 KB
- references/javascript/cucumber.cjs 442 B runs code
- references/javascript/extract-gherkin.cjs 7.9 KB runs code
- references/javascript/openspec-effective-paths.cjs 5.0 KB runs code
- references/javascript/SETUP.md 3.6 KB
- references/python/behave.ini 206 B
- references/python/environment.py 612 B runs code
- references/python/extract_gherkin.py 8.9 KB runs code
- references/python/openspec_effective_spec.py 5.9 KB runs code
- references/python/run_acceptance.py 1.5 KB runs code
- references/python/SETUP.md 3.6 KB
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.
- 1mo ago First seen · 121 lines · 51 tokens per session scan A bd2706d34c7e
acceptance-test-authoring is a skill published in the GitHub repository intent-driven-dev/intent-driven-template (169 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 1,793 once invoked, about $0.0002 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
agent-evaluation
A guide to measuring whether an AI agent works reliably on the tasks that matter. It covers repeatable test environments, program checks, human-like scoring rules, failure analysis, and experiments that separate model problems from system problems.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
gsd-add-tests
Generate tests for a completed phase based on UAT criteria and implementation.
gsd-audit-uat
Cross-phase audit of all outstanding UAT and verification items.
web-test
A browser-automation tool for testing the 1C:Enterprise web client. It uses Playwright to navigate sections, fill forms, read tables and reports, and perform user actions in a browser.
actionbook-web-test
Run browser-based web tests against websites using Actionbook CLI. Activate when the user wants to test a website workflow, run smoke tests, verify a user flow, check if a web application works, run regression tests, or validate browser-based interactions. Supports test definition, execution, assertion, reporting, and…