multi-agent-collaboration-system: Skill for Claude Code

.agents/skills/improve-ut/SKILL.md

improve-ut is a skill for Claude Code, Codex from lxyer/multi-agent-collaboration-system. It costs 75 tokens per session (407 once invoked), scanned A, original, MIT.

A workflow for improving unit tests, which check small pieces of code in isolation. It follows the project’s own testing rules and decides when broader integration or regression tests are needed.

In plain words
What is it for?
It is for inspecting changed files, adding or updating tests, choosing between unit, integration, and regression coverage, and running linting, type checks, and tests.
Why use it?
It helps add useful tests after code changes without guessing the project’s conventions or testing the wrong scope.

Skill for Claude CodeCodex

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

This is lxyer/multi-agent-collaboration-system's own configuration. It tells Claude Code and Codex how to work on multi-agent-collaboration-system 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 multi-agent-collaboration-system configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 ./.trellis/scripts/get_context.py --mode packages.

Reuse

Borrowing it

Nothing to install: this file belongs to lxyer/multi-agent-collaboration-system. 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/lxyer/multi-agent-collaboration-system/main/.agents/skills/improve-ut/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/lxyer/multi-agent-collaboration-system

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 improve-ut

README.md
[![agentmods](https://agentmods.dev/badge/skills/lxyer/multi-agent-collaboration-system/improve-ut/github.svg)](https://agentmods.dev/skills/lxyer/multi-agent-collaboration-system/improve-ut)
Your own site
<a href="https://agentmods.dev/skills/lxyer/multi-agent-collaboration-system/improve-ut"><img src="https://agentmods.dev/badge/skills/lxyer/multi-agent-collaboration-system/improve-ut/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.

agentmods 80×15 button for improve-ut

Your own site · 80×15
<a href="https://agentmods.dev/skills/lxyer/multi-agent-collaboration-system/improve-ut"><img src="https://agentmods.dev/badge/skills/lxyer/multi-agent-collaboration-system/improve-ut.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 407 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 $0.00075 $0.00407
Opus 5 $0.00037 $0.00204
Sonnet 5 $0.00015 $0.00081
Haiku 4.5 $0.00007 $0.00041

Measured 8d ago against content hash b63988e1b7de, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

improve-ut 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 8d 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/improve-ut/SKILL.md · 70 lines

What it actually says

Improve Unit Tests (UT)

Use this skill to improve test coverage after code changes.

Usage

$improve-ut

Source of Truth

Discover and read unit-test specs dynamically:

# Discover available packages and their spec layers
python3 ./.trellis/scripts/get_context.py --mode packages

Look for packages with unit-test spec layer in the output. For each discovered unit-test/ directory, read all relevant spec files inside it (for example index.md, conventions.md, integration-patterns.md, mock-strategies.md).

If this skill conflicts with the unit-test specs, the specs win.


Execution Flow

  1. Inspect changed files:
    • git diff --name-only
  2. Decide test scope using unit-test specs:
    • unit vs integration vs regression
    • mock vs real filesystem flow
  3. Add/update tests using existing project test patterns
  4. Run validation:
pnpm lint
pnpm typecheck
pnpm test
  1. Summarize decisions, updates, and remaining test gaps.

Output Format

## UT Coverage Plan
- Changed areas: ...
- Test scope (unit/integration/regression): ...

## Test Updates
- Added: ...
- Updated: ...

## Validation
- pnpm lint: pass/fail
- pnpm typecheck: pass/fail
- pnpm test: pass/fail

## Gaps / Follow-ups
- <none or explicit rationale>
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. 8d ago First seen · 70 lines · 75 tokens per session scan A b63988e1b7de

Subscribe to this mod's changes

improve-ut is a skill published in the GitHub repository lxyer/multi-agent-collaboration-system (1 stars, last pushed 4mo ago), licensed MIT. It adds 75 tokens to every session and 407 once invoked, about $0.0004 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.