Borrowing it
Nothing to install: this file belongs to Eduardo-Salvador/Agent-Harness-Kit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Eduardo-Salvador/Agent-Harness-Kit/main/.agents/skills/test-driven-task/SKILL.mdgit clone --depth 1 https://github.com/Eduardo-Salvador/Agent-Harness-KitWrote 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/eduardo-salvador/agent-harness-kit/test-driven-task)<a href="https://agentmods.dev/skills/eduardo-salvador/agent-harness-kit/test-driven-task"><img src="https://agentmods.dev/badge/skills/eduardo-salvador/agent-harness-kit/test-driven-task/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/eduardo-salvador/agent-harness-kit/test-driven-task"><img src="https://agentmods.dev/badge/skills/eduardo-salvador/agent-harness-kit/test-driven-task.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 | $0.00043 | $0.00434 |
| Opus 5.5 | $0.00017 | $0.00174 |
| Sonnet 5.5 | $0.00009 | $0.00087 |
| Haiku 4.5 | $0.00004 | $0.00043 |
Grade A, and why
test-driven-task 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 1mo 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
Test-driven task
Do not load this skill for direct-trivial or vibe. Vibe requires a focused deterministic check. Failed verification begins bounded in-scope recovery; promote only when a full-Harness condition is exposed.
- Read
../../../harness/playbooks/test-driven-execution.mdand the task'sTest-first cyclesection before editing code. - For
test_strategy: tdd, do not change production code before observing RED: add or select the focused test from the spec, run it, and confirm it fails for the intended missing behavior rather than syntax, environment, or an unrelated defect. - If the test passes before implementation or fails for the wrong reason, stop and return
needs-replan; do not fake RED, weaken the assertion, or edit production code until the spec/test is corrected. - Implement only the minimum behavior required for GREEN. Run the same focused test and record its passing result. Refactor only after GREEN, without broadening behavior, then run the focused test plus the spec's proportional regression set.
- Keep RED and GREEN inside the same small task and lease. Do not create a separate graph node that intentionally leaves the shared baseline failing.
- Record RED, GREEN, refactor, and the highest sufficient ladder rung (
focused→workspace→integration→global/checkpoint→delivery) in the transition/closeout. Create a handoff only for an actual separate consumer. characterizationis allowed only for a behavior-preserving refactor with no desired behavior delta.verification-onlyis allowed only for non-code/artifact work or when no meaningful automated behavior test applies; the task spec must state the exact exception. Once work entersfull-harness, simplicity, deadline, hackathon mode, or lack of an existing test is not by itself an exception.
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.
- 1mo ago Changed a593527cf156
- 2mo ago First seen · 17 lines · 43 tokens per session scan A aa9bed97b6b3
test-driven-task is a skill published in the GitHub repository Eduardo-Salvador/Agent-Harness-Kit (6 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 434 once invoked, about $0.0002 per session on Opus 5.5. 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
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code.
verification-before-completion
Use when about to claim work is complete, fixed, or passing, or before committing or creating PRs.
developing-openrig
Use when changing OpenRig's own source in a clone of the openrig repository: finding which package or file owns a behaviour, choosing which tests to run, testing a change without disturbing the OpenRig daemon your own session runs on, judging whether a diff touches a high-risk area, or preparing a pull request. Not…
qa
Run scalable, isolated live QA for nac development. The top-level local orchestrator must parse n (default 4), dispatch one setup worker with this skill, copy its n assignment contracts verbatim into exactly n parallel test workers with this skill, then dispatch one aggregate worker with this skill using all test…
ap-implementer
Report the compatibility redirect to ap-worker; this retired role cannot perform new work.
dogfood
Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -…