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 SebastienDegodez/copilot-instructions --skill outside-in-tddgit clone --depth 1 https://github.com/SebastienDegodez/copilot-instructionsWrote 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/sebastiendegodez/copilot-instructions/outside-in-tdd)<a href="https://agentmods.dev/skills/sebastiendegodez/copilot-instructions/outside-in-tdd"><img src="https://agentmods.dev/badge/skills/sebastiendegodez/copilot-instructions/outside-in-tdd/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/sebastiendegodez/copilot-instructions/outside-in-tdd"><img src="https://agentmods.dev/badge/skills/sebastiendegodez/copilot-instructions/outside-in-tdd.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 | $0.00035 | $0.01601 |
| Opus 5 | $0.00017 | $0.00800 |
| Sonnet 5 | $0.00007 | $0.00320 |
| Haiku 4.5 | $0.00003 | $0.00160 |
Grade A, and why
outside-in-tdd 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 11d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Outside-In DDD Testing
Overview
Complete testing guide for outside-in development. Start from observable behavior (Gherkin), let design emerge from tests.
Core rule: Real domain objects, mocked external boundaries, fast in-memory tests.
Outside-In Approach
Prerequisite: Gherkin scenarios must be written and approved before this skill applies. This includes new features, bug fixes, and behavior-changing refactoring. If Gherkin scenarios are already approved for the current task, proceed directly to Step 1 — gherkin-gate is already done.
REQUIRED SUB-SKILL: superpowers-whetstone:gherkin-gate — run first, wait for approval, then return here.
Step 1: Map Scenario to Acceptance Test
- Map Gherkin to test — translate scenario to a top-level acceptance-style test
- Write the test — mock only external boundaries, use real domain objects
Step 2: Let Domain Emerge
STOP. Do NOT create any domain class, value object, entity, policy, or enum before your first test fails to compile. Design MUST emerge from red — not from upfront thinking. Even if you already know the domain from context, create nothing until the test's compilation failure confirms what's needed. This includes adding 'just a new variant' of something that already exists: a new vehicle type, a new rejection reason, a new value object field, or a new boundary value — even if similar ones already exist in the codebase. Wait for the test's compilation failure before creating the new type.
Test failures reveal the domain you need. Let the design emerge from failing tests — don't design upfront.
- Domain objects (policies, value objects, services) emerge from what the test demands
- Orchestrators only coordinate — domain logic lives in the domain
- Real domain objects (not mocked)
- No design upfront — the test tells you what to build
Step 3: Verify with Mutation Testing
Once both acceptance and domain test streams are green:
REQUIRED SUB-SKILL: superpowers-whetstone:mutation-testing — run NOW, before merge. 100% on business logic, equivalent mutants are the only accepted survivors. This applies to ALL changes — not just new features. Bug fixes, refactoring, and edge case additions must also pass mutation testing if any test was written or changed to make this work.
What ships with it
5 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.
- 11d ago First seen · 155 lines · 35 tokens per session scan A c65990c93bf5
outside-in-tdd is a skill published in the GitHub repository SebastienDegodez/copilot-instructions (193 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 1,601 once invoked, about $0.0002 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
testing
TDD/BDD testing principles. Use when writing tests, reviewing test coverage, setting up testing, or discussing test strategy and test architecture.
workflow-analysis
Workflow d'Analyse Obligatoire. Use when working with workflow analysis.
outside-in-tdd
Use when an approved scenario, Gherkin example, worked example, or expected result has to become working software through outside-in / double-loop TDD -- start from an acceptance or application-boundary test, get a trustworthy RED before implementation, let domain logic emerge only from failing behavior, and drive one…
quality-gates-evidence-contract
Use when producing or verifying the structured evidence log that attests quality gates (tests, build, mutation, commits, RED/GREEN integrity). Tech-agnostic schema. Loaded by software-engineer (writer) at COMMIT phase and by quality-gates-lens (reader) during review.
quality-gates-dotnet
Use when the active repository is a .NET solution (.sln / .csproj present) and the software-engineer must produce falsifiable evidence for the quality gates. Most gates are captured at the end of the COMMIT phase; the G10 RED capture is taken at RED, before any production code, and cannot be reconstructed later.…
tdd-workflow
Test-Driven Development workflow principles. RED-GREEN-REFACTOR cycle.