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 mattwynne/yaks --skill bdd-discoverygit clone --depth 1 https://github.com/mattwynne/yaksWrote 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/mattwynne/yaks/bdd-discovery)<a href="https://agentmods.dev/skills/mattwynne/yaks/bdd-discovery"><img src="https://agentmods.dev/badge/skills/mattwynne/yaks/bdd-discovery/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/mattwynne/yaks/bdd-discovery"><img src="https://agentmods.dev/badge/skills/mattwynne/yaks/bdd-discovery.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 | $0.00029 | $0.00504 |
| Opus 5 | $0.00015 | $0.00252 |
| Sonnet 5 | $0.00006 | $0.00101 |
| Haiku 4.5 | $0.00003 | $0.00050 |
Grade A, and why
bdd-discovery 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 10d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BDD Discovery
Discovery is the conversation before formulation. Use it to build shared understanding of a story: the rules, examples, questions, and scope boundaries that matter.
For writing or refining Gherkin, use bdd-formulation.
Example Mapping
Map one story with the Three Amigos: product, development, and testing. Keep it small, low-tech, and time-boxed.
Cards:
- Story: the work under discussion.
- Rules: business rules, constraints, policies, or acceptance criteria.
- Examples: concrete cases that illustrate one rule.
- Questions: unknowns, assumptions, missing decisions, or research.
- New stories: behaviour discovered but sliced out of scope.
Traditional colours: yellow story, blue rules, green examples, red questions.
How to Run It
- Start with the story and the rules people already know.
- Ask for concrete examples for each rule.
- Put each example under the rule it illustrates.
- Capture uncertainty as questions; do not solve everything in the room.
- Capture tangents or large discoveries as new stories.
- Stop when the story is clear enough to pull, or the time-box expires.
Discovery Habits
- Prefer conversation over documents.
- Use domain language, not implementation details.
- Talk about behaviour as if it could be handled manually.
- Keep examples rough but concrete: real names, amounts, states, dates.
- Treat red cards as progress: unknown unknowns became known unknowns.
- Let rules and examples reveal better story slices.
Reading the Map
- Many red cards: too much uncertainty; research or invite the right person.
- Many blue cards: story may be too broad or complex.
- Many green cards under one rule: the rule may hide smaller rules.
- New story cards: useful scope control, not failure.
Ready for Formulation?
Move to bdd-formulation when:
- The team agrees what problem the story solves.
- Key rules are visible.
- Risky or unclear rules have concrete examples.
- Open questions are captured and owned.
- Out-of-scope behaviour is sliced away.
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.
- 10d ago First seen · 67 lines · 29 tokens per session scan A d3f1ea42c0a1
bdd-discovery is a skill published in the GitHub repository mattwynne/yaks (58 stars, last pushed 28d ago), licensed MIT. It adds 29 tokens to every session and 504 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
coding
Use when five specialized coding agents (linter, perf, refactor, security, test) that enforce quality gates across the development lifecycle. From lint enforcement through performance profiling, refactoring, security auditing, and test coverage. Use when working with coding agents.
test-agent
Use when writing comprehensive test suites covering happy paths, error paths, edge cases, and integration points.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code.
tdd
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.
chaos-fault-injection
Deliberately inject faults — dropped connections, corrupted writes, latency, malformed responses, resource exhaustion — and assert the system's expected recovery (escalation, hardstop, rollback).
metamorphic-testing
Test systems with no reliable oracle using metamorphic relations — equivalence-preserving input transforms whose outputs must agree, with concrete relations for LLM/NLP stability.