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/0xrafasec/ai-workflow/tddnpx skills add 0xrafasec/ai-workflow --skill tddgit clone --depth 1 https://github.com/0xrafasec/ai-workflowWrote 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/0xrafasec/ai-workflow/tdd)<a href="https://agentmods.dev/skills/0xrafasec/ai-workflow/tdd"><img src="https://agentmods.dev/badge/skills/0xrafasec/ai-workflow/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 | $0.00093 | $0.01592 |
| Opus 5 | $0.00046 | $0.00796 |
| Sonnet 5 | $0.00019 | $0.00318 |
| Haiku 4.5 | $0.00009 | $0.00159 |
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 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create the Technical Design Document. Argument: $ARGUMENTS
Context Gathering
Before interviewing, explore the project's current build and test setup:
-
Check for existing docs:
- Read
docs/TECHNICAL_DESIGN_DOCUMENT.md— if revising, don't start from scratch - Read
CLAUDE.mdfor build/test commands - Read
docs/ARCHITECTURE.mdif it exists (for technology context) - Read
README.mdfor setup instructions
- Read
-
Explore the codebase:
- Look for test directories (
tests/,__tests__/,spec/,*_test.go,*.test.ts,test_*.py) - Read
package.json,pyproject.toml,Cargo.toml,Makefile,docker-compose.ymlfor tooling, test commands, dependencies - Read 1-2 existing test files to understand patterns (fixtures, helpers, naming)
- Check for CI config (
.github/workflows/,.gitlab-ci.yml,Jenkinsfile) - Check for linter/formatter config (
.eslintrc,ruff.toml,.golangci.yml,rustfmt.toml) - Summarize what you found to the user before starting — "Here's what I see in the project: ..."
- Look for test directories (
Interview
Use AskUserQuestion to understand how the team builds, tests, and ships. Adapt based on what the codebase already reveals.
- Testing strategy — What test frameworks are in use? Where do tests live? Are there separate unit/integration/e2e layers? What needs integration tests vs unit tests? Any critical flows that need e2e coverage?
- Dev environment — How do developers set up locally? Docker, nix, manual install? What external services are needed (databases, queues, caches)?
- CI/CD pipeline — What runs on every PR? What runs nightly? What gates block merging? How are deployments triggered?
- Coding standards — Linter config, formatter, type checker? Any style guides or conventions not captured in tooling?
- Tooling decisions — Package manager, build system, monorepo tools? Why these over alternatives?
- Error handling & observability — Logging framework, error tracking, metrics? How do you debug production issues?
- Dependencies — How are deps managed? Pinned versions? Vulnerability scanning? Update cadence?
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 · 138 lines · 93 tokens per session scan A dd19f3a0a01a
tdd is a skill published in the GitHub repository 0xrafasec/ai-workflow (9 stars, last pushed 3d ago), licensed MIT. It adds 93 tokens to every session and 1,592 once invoked, about $0.0005 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
nunit-build-infra
Use when editing .csproj, .nuspec, Directory.Build.props, Directory.Build.targets, Directory.Packages.props, the Cake build (build.cake, build.ps1, build.sh), or GitHub Actions workflows. Covers central package management, MinVer-driven versioning, the props-vs-targets split, and nuspec/csproj consistency.
gem-devops-guidelines
Design or review infrastructure, deployment, CI/CD, Docker, Kubernetes, health checks, rollback, feature flags, production readiness, and mobile release workflows. Use for DevOps, platform, container, pipeline, or release tasks.
gh-ci-watch
Use when 需要監看或查詢 GitHub Actions（push 後盯 CI / deploy 綠燈、等某 run 或某 SHA 完成、撈 run log 證據、查 runner 佇列）。NOT for 修 CI 紅燈本身（那是拿到結果後的除錯流程）。.
data-quality-frameworks-sickn33
Implement data quality validation with Great Expectations, dbt tests, and data contracts. Use when building data quality pipelines, implementing validation rules, or establishing data contracts.
ai-agents-validation-and-qa
What counts as evidence in ai-agents and how to produce it. Covers the TESTING-RIGOR pos+neg+edge bar, test layout and collection reality, coverage proof commands, runtime-contract tests with negative controls, and ADR-034 QA skip semantics at session end. Use when you say what counts as evidence, how do I test this…
init-pipeline
Infrastructure skill for scaffolding pipeline enforcement into a project. Sets up Claude Code hooks (TDD classification gate, git guardrails, optional quality gate), pre-commit hooks (detects existing tools, defaults to Lefthook + Biome + pnpm if none found). Run when setting up a project for pipeline work, and again…