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 agentmods add skills/robconery/cassini-workshop/bdd-specsnpx skills add robconery/cassini-workshop --skill bdd-specsgit clone --depth 1 https://github.com/robconery/cassini-workshopWrote 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/robconery/cassini-workshop/bdd-specs)<a href="https://agentmods.dev/skills/robconery/cassini-workshop/bdd-specs"><img src="https://agentmods.dev/badge/skills/robconery/cassini-workshop/bdd-specs.svg" alt="Measured on agentmods" 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 | $0.00183 | $0.01708 |
| Opus 5 | $0.00092 | $0.00854 |
| Sonnet 5 | $0.00037 | $0.00342 |
| Haiku 4.5 | $0.00018 | $0.00171 |
Grade A, and why
bdd-specs 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 5d 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Behavior-Driven Design — Specifications First
Specifications are written before implementation. The spec is the design artifact: it encodes the intended behavior from the plan and the user stories, fails first, and is the definition of done. Do not write implementation code under this skill until the specs exist and the user has seen them.
🎯 Why: Design for Change
The goal of writing software is to be able to change it safely. Specs are the safety net that makes change possible — without them, every edit is a guess. One assertion per Specification means a failing spec names exactly what broke; happy/sad-path separation means you can change one behavior without re-reading the whole suite. The spec suite is the change-budget for the codebase.
The non-negotiable workflow
Run these gates in order. Do not skip ahead.
1. Require the plan
Look for the build plan at /docs/PLAN.md (also accept
docs/PLAN.md, PLAN.md, or an obvious docs/plan.*).
- If it is missing: stop. Ask the user to provide a
PLAN.mdin/docs. Offer to scaffold one fromtemplates/PLAN.mdand let them fill it in, or to draft it from their description and write it to/docs/PLAN.mdfor approval. Do not proceed to specs without an approved plan. - If it exists: read it fully. It defines the features and the technical boundaries the specs must cover.
2. Require the user stories
Look for user stories at /docs/STORIES.md (also accept
docs/STORIES.md, STORIES.md).
- If it is missing: stop. Ask the user for the user stories. Offer
to scaffold
templates/STORIES.md, or to derive draft stories fromPLAN.mdand write them to/docs/STORIES.mdfor approval. Do not proceed without stories — they are the source of every Scenario. - If it exists: read it fully. Each story maps to one Feature; each acceptance criterion / "so that" outcome maps to a Scenario.
3. Detect the test runner
Pick the runner from the project, do not ask:
What ships with it
6 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.
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.
- 5d ago First seen · 163 lines · 183 tokens per session scan A 0ebc2a40b557
bdd-specs is a skill published in the GitHub repository robconery/cassini-workshop (1 stars, last pushed 2mo ago), licensed MIT. It adds 183 tokens to every session and 1,708 once invoked, about $0.0009 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
bdd-specs
Behavior-driven design: write executable specifications BEFORE any implementation code. Reads /docs/PLAN.md for the build plan and /docs/STORIES.md for user stories, and stops to ask for either if it is missing. Generates TypeScript spec files in nested blocks — Feature > Scenario > Specification — where each Scenario…
tdd
Test-driven development with bun:test, written for clarity. Produces failing tests FIRST — before any implementation — that read as the executable spec a builder agent implements against. Each test names a single behavior in plain language, follows Arrange–Act–Assert, asserts one thing, and uses real types with no…
test-driven-development
Test-Driven Development enforces the RED-GREEN-REFACTOR discipline on every code change an agent produces.
test-driven-development
Strict red-green-refactor TDD for webhook.co. Use when implementing or changing behavior — especially correctness-critical paths (signing/verification, dedup/idempotency, retries, ordering, replay, metering). Tests must fail before any implementation.
Pair Programming
AI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with…
bdd-specs
Behavior-driven design: write executable specifications BEFORE any implementation code. Reads /docs/PLAN.md for the build plan and /docs/STORIES.md for user stories, and stops to ask for either if it is missing. Generates TypeScript spec files in nested blocks — Feature > Scenario > Specification — where each Scenario…