adev:write-test

A test-writing skill for TDD, a method where tests are written before the code they check. It creates failing tests first and checks that those tests were not changed improperly afterward.

In plain words
What is it for?
Writing the initial failing tests from a specification, source interface, or description, creating handoff notes, checking mocking boundaries, and verifying tests after implementation.
Why use it?
It gives implementation a clear behavioral target and helps prevent tests from being weakened or tailored just to pass.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/agentic-development/adev-plugin/write-test
Any agent
npx skills add agentic-development/adev-plugin --skill write-test
Clone the repo
git clone --depth 1 https://github.com/agentic-development/adev-plugin

Made for: Claude Code, Codex.

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,469 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00044 $0.07469
Opus 5 $0.00022 $0.03735
Sonnet 5 $0.00009 $0.01494
Haiku 4.5 $0.00004 $0.00747

Measured 2d ago against content hash 806bda0fd02c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

adev:write-test 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.

The scan reads SKILL.md. This mod also ships 3 executable files (detect-framework.sh, detect-gaming.sh, write-handoff.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

providers/codex/skills/write-test/SKILL.md · 597 lines

How it starts

The opening of the file, as written. The whole thing — 597 lines — stays where its author put it; the contents beside it link to each section on GitHub.

adev:write-test

Identity: TDD integrity specialist. Authors failing tests (RED phase), produces immutable handoff blocks, detects specification gaming, enforces mocking boundaries, and verifies post-GREEN test tamper.


Invocation Modes

adev:write-test --red --spec <path>           # Author tests from a Live Spec
adev:write-test --red --file <path>           # Author tests from a source file's interface
adev:write-test --red "<description>"         # Author tests from free-form behavioral description
adev:write-test --verify --packet <path>      # Post-GREEN tamper check against Handoff Block
adev:write-test --red --spec <path> --no-infra  # Skip infrastructure preflight (user-only)

Standalone invocation (any --red mode) presents a pre-flight summary before authoring. Dispatched by adev:implement (no pre-flight summary — context already confirmed).


Step 0: Standalone Pre-flight

When invoked directly (not dispatched by adev:implement):

  1. Detect framework (Step 2) and report the result.
  2. Show a pre-flight summary:
    Framework:       <detected framework>
    Target:          <spec path / file path / "inline-description">
    Est. contracts:  <N behavioral statements → N-M tests>
    Output path:     .context-index/packets/<slug>-tests.md
                     (fallback: ./packets/<slug>-tests.md if .context-index/ absent)
    
  3. Ask: "Proceed? (y/N)"
  4. If the user cancels, stop cleanly.

.context-index/-free operation: If .context-index/ does not exist, proceed without constitution or spec context. Apply all enforcement rules independently. Write the Handoff Block to ./packets/<slug>-tests.md.

Depth pin (Behavior 17): Standalone invocation — --red --spec, --red --file, or --red "<description>", with or without .context-index/ — always authors at the built-in standard depth. It performs no chain resolution, no escalation, and no floor evaluation, and it emits no test_depth_assigned event, because there is no plan task to key one to. Standalone mode reads no test-depth policy configuration at all. When this skill is instead dispatched from /adev:implement (non-standalone), the depth passed in the subagent prompt is authoritative and this pin does not apply.

Read the full file on GitHub · 597 lines

Files

What ships with it

4 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.

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 First seen · 597 lines · 44 tokens per session scan A 806bda0fd02c

Subscribe to this mod's changes

adev:write-test is a skill published in the GitHub repository agentic-development/adev-plugin (11 stars, last pushed 2d ago), licensed MIT. It adds 44 tokens to every session and 7,469 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens