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 johnqtcg/awesome-skills --skill tdd-workflowgit clone --depth 1 https://github.com/johnqtcg/awesome-skillsWrote 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/johnqtcg/awesome-skills/tdd-workflow)<a href="https://agentmods.dev/skills/johnqtcg/awesome-skills/tdd-workflow"><img src="https://agentmods.dev/badge/skills/johnqtcg/awesome-skills/tdd-workflow/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/johnqtcg/awesome-skills/tdd-workflow"><img src="https://agentmods.dev/badge/skills/johnqtcg/awesome-skills/tdd-workflow.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 | $0.00065 | $0.02668 |
| Opus 5 | $0.00032 | $0.01334 |
| Sonnet 5 | $0.00013 | $0.00534 |
| Haiku 4.5 | $0.00006 | $0.00267 |
Grade A, and why
tdd-workflow 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 7d 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 — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Go TDD Workflow
Apply TDD end-to-end: write failing tests first, implement minimal code, refactor safely, and prove quality with coverage plus risk-path checks.
Hard Rules
- Start with tests, not implementation.
- Preserve visible
Red -> Green -> Refactorevidence in commands/output. - Keep test files co-located and named
<target>_test.go. - Assertion strategy (adapt to project):
- If project uses testify:
requirefor fatal preconditions,assertfor value checks. - If project uses standard library only: use
t.Fatalffor fatal,t.Errorffor value checks; include got/want:t.Errorf("Name = %q, want %q", got, want). - If project uses go-cmp: use
cmp.Difffor deep struct comparison. - Detection: Check existing
_test.gofiles for"github.com/stretchr/testify"imports. Follow project convention.
- If project uses testify:
- Prefer table-driven tests with
t.Run. - Prefer real deps or lightweight fakes; avoid heavy mock chains by default.
- Do not add speculative production code not required by failing tests.
New Mandatory Gates
1) Defect Hypothesis Gate
Before writing tests, list concrete defect hypotheses from target code:
- boundary/index (
n-1,i+1, last-item behavior) - error propagation/wrapping
- mapping loss/data mismatch
- concurrency/order/timing
- idempotency/retry behavior
Each hypothesis must map to at least one test case name. For detailed defect-hypothesis patterns and BAD/GOOD examples, cross-reference the unit-test skill: references/bug-finding-techniques.md, references/killer-case-patterns.md, and Fixed Boundary Checklist.
2) Killer Case Gate
Per changed method/use-case, add at least one killer case that:
- targets a high-risk defect hypothesis
- includes assertion(s) that must fail on known bad mutation/path
- is explicitly marked in report
3) Coverage Gate (Line + Risk Path)
- Line coverage gate: changed package(s) >=80% by default.
- Risk-path gate: all high-risk branches/hypotheses must be covered even if line coverage already passes.
- If gate waived, require explicit user approval and documented risk.
What ships with it
18 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.
- references/anti-examples.md 3.3 KB
- references/api-3layer-template.md 4.4 KB
- references/boundary-checklist.md 3.1 KB
- references/fake-stub-template.md 1.5 KB
- references/golden-characterization-example.md 5.3 KB
- references/tdd-workflow.md 5.2 KB
- scripts/run_regression.sh 313 B runs code
- scripts/tests/COVERAGE.md 6.2 KB
- scripts/tests/golden/001_s_bugfix_off_by_one.json 1.2 KB
- scripts/tests/golden/002_s_bugfix_error_swallowed.json 1.2 KB
- scripts/tests/golden/003_m_feature_new_endpoint.json 1.4 KB
- scripts/tests/golden/004_m_feature_business_rule.json 1.2 KB
- scripts/tests/golden/005_l_feature_transfer_funds.json 1.5 KB
- scripts/tests/golden/006_refactor_extract_method.json 1.3 KB
- scripts/tests/golden/007_legacy_code_characterization.json 1.2 KB
- scripts/tests/golden/008_concurrency_safety.json 1.3 KB
- scripts/tests/test_golden_scenarios.py 6.8 KB runs code
- scripts/tests/test_skill_contract.py 13 KB runs code
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.
- 7d ago First seen · 269 lines · 65 tokens per session scan A e365db639537
tdd-workflow is a skill published in the GitHub repository johnqtcg/awesome-skills (30 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 2,668 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
verify-implementation
A workflow that runs a project’s verification skills to produce a report on coding patterns, architecture rules, and project conventions. It is intended for work after implementation, before a pull request, or during code review.
verification-engine
Use when verifying build/test/lint before commit, PR, or completion claims. Runs verification pipeline in fresh subagent context with auto-repair. Triggers on /handoff-verify, pre-commit check, build verification, test validation.
ci-tests
Run the test suite for the current repo, auto-detecting Python (pytest/uv), Node (vitest/pnpm), or Rust (cargo test).
typescript-eval
Test TypeScript code snippets before persisting as skills.
eval-harness
Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles.
dependency-upgrade
Manage major dependency version upgrades with compatibility analysis, staged rollout, and comprehensive testing. Use when upgrading framework versions, updating major dependencies, or managing breaking changes in libraries.