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 bharat3645/The-Ideal-Harness --skill tddgit clone --depth 1 https://github.com/bharat3645/The-Ideal-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/bharat3645/the-ideal-harness/tdd)<a href="https://agentmods.dev/skills/bharat3645/the-ideal-harness/tdd"><img src="https://agentmods.dev/badge/skills/bharat3645/the-ideal-harness/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/bharat3645/the-ideal-harness/tdd"><img src="https://agentmods.dev/badge/skills/bharat3645/the-ideal-harness/tdd.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00062 | $0.00468 |
| Opus 5 | $0.00031 | $0.00234 |
| Sonnet 5 | $0.00012 | $0.00094 |
| Haiku 4.5 | $0.00006 | $0.00047 |
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 12d 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 (red, green, refactor)
subagent-driven-development's ledger verifies a whole TASK is done via verify.command. This
skill is the finer-grained discipline for the code written INSIDE one task: prove the test fails
for the right reason before making it pass, one small cycle at a time. The two compose — a task's
verify.command is often literally "run the test suite this skill was used to write."
Process
- Write one test for the next smallest behavior, not the whole feature. Name it for the behavior, not the implementation ("rejects a negative amount", not "test3").
- Run it and confirm it fails for the stated reason — a test that passes before the code exists, or fails with an unrelated error, proves nothing. Read the actual failure output.
- Write the minimum code to pass it. Resist writing more than the current test demands; the next test will demand the next piece.
- Run the full local suite, not just the new test — a green new test next to a broken old one is not progress.
- Refactor with the tests green, if the code asks for it. Never refactor and add behavior in the same step — that's two changes wearing one commit.
- Repeat from 1.
Boundary
This is a per-change discipline, not a project methodology mandate — some code (glue, config,
generated bindings) isn't worth testing this granularly, and this skill doesn't override that
judgment. It also isn't a substitute for the ledger's task-level verify.command: a task can pass
every unit test this cycle produced and still fail its real acceptance check (e.g. an integration
behavior no unit test covers) — the ledger's verify is still the thing that decides "done."
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.
- 12d ago First seen · 35 lines · 62 tokens per session scan A 7c751bb4f0f0
tdd is a skill published in the GitHub repository bharat3645/The-Ideal-Harness (5 stars, last pushed 2d ago), licensed MIT. It adds 62 tokens to every session and 468 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 2026-08-31.
Other skills, from other repositories
ax-agent-optimize
This skill helps an LLM generate correct AxAgent tuning and evaluation code using @ax-llm/ax. Use when the user asks about agent.optimize(...), judgeOptions, eval datasets, optimization targets, saved optimizedProgram artifacts, or agent optimization guidance.
output-dev-eval-testing
Create offline evaluation tests for Output SDK workflows using @outputai/evals. Use when implementing test evaluators with verify(), creating dataset YAML files, building eval workflows, or running workflow tests via CLI.
output-eval-validate-judge
Validate LLM judges against human labels using TPR/TNR metrics and train/dev/test splits. Use after writing a judge prompt to verify it agrees with human judgment.
output-dev-scenario-file
Create test scenario JSON files for Output SDK workflows. Use when creating test inputs, documenting expected behaviors, or setting up workflow testing.
agent-browser
Automates browser and Electron app interactions for user-flow validation.
benchmark-validator
Benchmark validation procedure for one assigned benchmark-related target. For optimization EXP- targets, independently classify candidate outcome. For engineering VAL- or legacy engineering targets, prove or disprove the required benchmark/performance assertion.