write-tests

A workflow for writing tests after studying the codebase’s existing test style, public interfaces, dependencies, and likely edge cases. It covers normal inputs, invalid data, errors, empty values, and boundaries.

In plain words
What is it for?
Use it to add test files, expand coverage, test exported functions, match the project’s test runner and assertions, and validate the new tests.
Why use it?
It avoids tests that merely follow implementation details or conflict with the project’s established testing conventions.

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/edimuj/tokenlean/write-tests
Any agent
npx skills add edimuj/tokenlean --skill write-tests
Clone the repo
git clone --depth 1 https://github.com/edimuj/tokenlean

Made for: Claude Code, Codex.

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 679 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 $0.00052 $0.00679
Opus 5 $0.00026 $0.00340
Sonnet 5 $0.00010 $0.00136
Haiku 4.5 $0.00005 $0.00068

Measured yesterday against content hash cb0761184b5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

write-tests 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 yesterday.

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.

skills/claude/write-tests/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Write Tests

Write tests that match project conventions and cover real edge cases.

Workflow

Discover → Understand → Design → Write → Validate

1. Discover

Find the testing landscape:

tl parallel \
  "testmap=tl test-map <file>" \
  "coverage=tl coverage <file>" \
  "example=tl example '*.test.*'" \
  "style=tl style"

2. Understand

Know the code before testing it:

tl parallel \
  "symbols=tl symbols <file>" \
  "exports=tl exports <file>" \
  "deps=tl deps <file>"
tl snippet <function> <file>   # Read each function to understand branches and edge cases

3. Design

For each exported function, identify:

  • Happy path (normal input, expected output)
  • Error cases (invalid input, missing data, exceptions)
  • Edge cases (empty input, boundary values, null/undefined)
tl parallel "flow=tl flow <function> <file>" "types=tl types <file>"

4. Write

  • Follow the pattern from existing test files found in step 1
  • Match the project's test runner, assertion style, and file naming
  • Colocate test files with source (or match existing convention)
  • Mock external dependencies identified by tl deps, not internal functions

5. Validate

tl parallel \
  "new=tl run '<test command> <new-test-file>'" \
  "coverage=tl coverage <file>" \
  "full=tl run '<full test suite>'"

Decision tree

Write tests → Do tests already exist for this file?
  ├─ Yes (extend) → tl test-map to find the test file
  │   → tl symbols on the test file to see what's covered
  │   → tl coverage to find gaps
  │   → Add missing cases following existing patterns
  ├─ No (create) → tl example "*.test.*" to learn project patterns
  │   → tl exports on source to prioritize public API
  │   → tl deps to identify what to mock
  │   → Create test file matching project conventions
  └─ Coverage target → tl coverage for current numbers
      → tl symbols to list all functions
      → Prioritize: exported > complex > simple
      → Write tests until target met

Read the full file on GitHub · 93 lines

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. yesterday First seen · 93 lines · 52 tokens per session scan A cb0761184b5d

Subscribe to this mod's changes

write-tests is a skill published in the GitHub repository edimuj/tokenlean (11 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 679 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 2026-08-30.

Related

Other skills, from other repositories

zerodust

Sweep 100% of native gas tokens (ETH, BNB, MATIC, etc.) from EVM chains via ZeroDust, leaving exactly zero balance. Use when: user wants to exit a chain completely, consolidate dust balances, clean up wallets, or bridge remaining native tokens cross-chain. Supports 25 mainnet chains including Ethereum, Base, Arbitrum…

andresdefi/zerodust · 93 tokens

ctx2img

Cut context tokens by rendering it as images. ctx2img paint turns any text-shaped input (a repo, a directory, a file, markdown, stdin) into dense images that carry the full text at 60-75% fewer tokens, with stable handles and a verbatim factsheet; ctx2img read recovers guaranteed-exact text. Use before ingesting any…

Koukyosyumei/h5i-ctx2img · 103 tokens

r3f-animation

React Three Fiber animation - useFrame, useAnimations, spring physics, keyframes. Use when animating objects, playing GLTF animations, creating procedural motion, or implementing physics-based movement.

zebbern/claude-code-guide · 43 tokens

r3f-best-practices

React Three Fiber (R3F) and Poimandres ecosystem best practices. Use when writing, reviewing, or optimizing R3F code. Triggers on tasks involving @react-three/fiber, @react-three/drei, zustand, @react-three/postprocessing, @react-three/rapier, or leva.

zebbern/claude-code-guide · 74 tokens

log-error-digest

Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…

zebbern/claude-code-guide · 71 tokens

vs-search

Search runtime and scene management: verify queries, inspect scenes, debug app readiness, and diagnose recall or scene-config issues.

volcengine/SearchCLI · 27 tokens