Agent-Harness-Kit: Skill for Claude Code

.agents/skills/test-driven-task/SKILL.md

test-driven-task is a skill for Claude Code, Codex from Eduardo-Salvador/Agent-Harness-Kit. It costs 43 tokens per session (434 once invoked), scanned A, original, MIT.

A workflow for changing code by writing a focused test first, then implementing the smallest behavior needed to pass it. TDD, or test-driven development, means using this failing-test-then-passing-test cycle.

In plain words
What is it for?
Use it for larger behavior changes and bug fixes that need full test-harness verification, while excluding trivial edits and small local changes covered by faster checks.
Why use it?
It catches incorrect assumptions early and requires behavior changes and bug fixes to have a proportional regression check.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is Eduardo-Salvador/Agent-Harness-Kit's own configuration. It tells Claude Code and Codex how to work on Agent-Harness-Kit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Agent-Harness-Kit configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/Eduardo-Salvador/Agent-Harness-Kit/main/.agents/skills/test-driven-task/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Eduardo-Salvador/Agent-Harness-Kit

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for test-driven-task

README.md
[![agentmods](https://agentmods.dev/badge/skills/eduardo-salvador/agent-harness-kit/test-driven-task.svg)](https://agentmods.dev/skills/eduardo-salvador/agent-harness-kit/test-driven-task)
Your own site
<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="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 434 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.00434
Opus 5 $0.00022 $0.00217
Sonnet 5 $0.00009 $0.00087
Haiku 4.5 $0.00004 $0.00043

Measured 2d ago against content hash a593527cf156, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

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 2d 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.

.agents/skills/test-driven-task/SKILL.md · 17 lines

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.

  1. Read ../../../harness/playbooks/test-driven-execution.md and the task's Test-first cycle section before editing code.
  2. 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.
  3. 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.
  4. 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.
  5. 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.
  6. Record RED, GREEN, refactor, and the highest sufficient ladder rung (focusedworkspaceintegrationglobal/checkpointdelivery) in the transition/closeout. Create a handoff only for an actual separate consumer.
  7. characterization is allowed only for a behavior-preserving refactor with no desired behavior delta. verification-only is 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 enters full-harness, simplicity, deadline, hackathon mode, or lack of an existing test is not by itself an exception.
Changes

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.

  1. 2d ago Changed a593527cf156
  2. 7d ago First seen · 17 lines · 43 tokens per session scan A aa9bed97b6b3

Subscribe to this mod's changes

test-driven-task is a skill published in the GitHub repository Eduardo-Salvador/Agent-Harness-Kit (6 stars, last pushed 3d ago), licensed MIT. It adds 43 tokens to every session and 434 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.