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 OutlineDriven/odin-claude-plugin --skill tddgit clone --depth 1 https://github.com/OutlineDriven/odin-claude-pluginWrote 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/outlinedriven/odin-claude-plugin/tdd)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/tdd"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/tdd.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 | $0.00080 | $0.01408 |
| Opus 5 | $0.00040 | $0.00704 |
| Sonnet 5 | $0.00016 | $0.00282 |
| Haiku 4.5 | $0.00008 | $0.00141 |
Grade A, and why
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 3d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Offensive-first TDD
Classic agent TDD rots in a known way: the red test is written as a polite specification, the implementation drifts, and the agent — lacking the metacognition to notice — bends fixtures, weakens assertions, and monkey-patches contracts until green appears. The tokens burn twice and the suite proves nothing. This skill inverts the stance. Red is an attack, not a description: before any implementation, write the tests that try to BREAK the contract — boundary raids, invariant violations, error-path probes, adversarial orderings. Green means the attacks failed to break the code, never that a fixture was satisfied.
Contract
| Field | Bound contract |
|---|---|
| Trigger | Develop a fix or feature test-first, plan a multi-step TDD build from a spec, or work behaviour red-to-green in slices. |
| Authority | Reversible-local: write only named test and source files; rollback via VCS revert of the implementation commit. Tests and implementation never change in the same repair step. |
| Side effect | Adds an attack suite and the minimal implementation that survives it, one vertical slice at a time; multi-step work also writes a plan document. |
| Done | Per slice: every contract clause has an attack that failed red for the right reason and passes green unweakened, plus one mutation probe the suite caught. Named evidence: test paths, failing output, passing output, probe output. |
Inputs
- Target and requirement (required): the behavior to build or fix, and the public seam where it is observed. A seam is confirmed with the user before any test exists at it.
- Contract source (required): spec, caller evidence, or known-good literals — the independent truth attacks are derived from. Never the implementation's own logic.
- Test framework (optional if discoverable): the project's runner. Stop and report if absent and not discoverable; never install one unasked.
Refusals
- Never weaken an assertion, bend a fixture, skip a test, or loosen a contract to reach green. Any such edit during a green phase is a stop-the-line violation: revert it, then either fix the implementation or declare a contract change and re-attack from red.
- Never edit a test and its implementation in the same repair step. Test-fixing and code-fixing are separate cycles, each with a named justification.
- Never accept a tautological attack (expected value recomputed the way the code computes it) or an implementation-coupled one (mocks internals, tests private methods). Attacks fire at confirmed public seams only.
- Not for hardening existing code with no behavior change — use tests-adversarial. Not for deleting weak tests — use tests-purge-unneeded.
What ships with it
1 file 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.
- 3d ago First seen · 56 lines · 80 tokens per session scan A afe0ef52d970
tdd is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed today), licensed Apache-2.0. It adds 80 tokens to every session and 1,408 once invoked, about $0.0004 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 2026-09-04.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…