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/mrlarson2007/copilot-tdd-harness/tdd-commitnpx skills add mrlarson2007/copilot-tdd-harness --skill tdd-commitgit clone --depth 1 https://github.com/mrlarson2007/copilot-tdd-harnessWrote 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/mrlarson2007/copilot-tdd-harness/tdd-commit)<a href="https://agentmods.dev/skills/mrlarson2007/copilot-tdd-harness/tdd-commit"><img src="https://agentmods.dev/badge/skills/mrlarson2007/copilot-tdd-harness/tdd-commit.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 | $0.00036 | $0.00220 |
| Opus 5 | $0.00018 | $0.00110 |
| Sonnet 5 | $0.00007 | $0.00044 |
| Haiku 4.5 | $0.00004 | $0.00022 |
Grade A, and why
tdd-commit 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.
What it actually says
TDD Commit Phase Skill
Purpose
- Create an atomic commit for the green state
- Enforce one-commit-per-green discipline
- Require clear, descriptive commit messages
- No refactor or new behavior in this phase
Inputs
- Green status
- Commit scope and message template
- Skill and asset references
Outputs
- Commit sha
- Files committed
- Commit message
Steps
- Load asset files for commit discipline, message quality, and anti-patterns
- Create atomic commit for green state
- Return contract output
Completion Checks
- Only green changes committed
- Commit message is clear and descriptive
- No refactor or new behavior included
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 · 39 lines · 36 tokens per session scan A f0677738825b
tdd-commit is a skill published in the GitHub repository mrlarson2007/copilot-tdd-harness (5 stars, last pushed 3mo ago), licensed MIT. It adds 36 tokens to every session and 220 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 2026-08-31.
Other skills, from other repositories
invokta-delivery
Deliver Invokta milestones and work items with TDD, adherence to versioned contracts and architecture, complete validation, and one cohesive commit per work item. Use when developing features, fixing bugs, executing roadmap milestones, or completing acceptance criteria in this repository.
dx-tdd
Execute the next pending phase of a change's plan test-first — red, green, refactor — and commit.
handle-issue
Take a tracked GitHub issue in aiops-platform from triage through SPEC/upstream investigation, TDD implementation, and local gates to an open PR, then hand off to handle-pr / gh-pr-follow-through. Use when starting work on an issue here — "处理下一个 issue", "修.
turnstile-core
Turnstile's non-negotiable rules -- gate order, TDD, brain-first, commit and reply conventions. Auto-loads whenever any turnstile skill is active.
901-feature-loop
Use 901 to run one feature end-to-end through SpecFlow's full pipeline as a single git-tracked run: high-level design, happy-path specs, scenario-by-scenario test-driven build-out validated and committed per module, cleanup, an optional expanded-coverage round, and a merge back to the base branch. Every design/spec…
tcrdd
Test-Commit-Revert + TDD (TCRDD): red/green/refactor with per-phase auto-commit on success and auto-revert on failure, gated by user approval before code and before committing. TRIGGER when: user says TCRDD, TCR, TDD, red-green-refactor, "test-first", "write the test first", "let's TDD this", "baby steps", "commit on…