agentmods.dev

coware

coware is a skill for Claude Code from shitianfang/coware-skills. It costs 100 tokens per session (2,372 once invoked), scanned A, original, MIT.

A shared specification system for teams of AI coding agents. Coware pulls and synchronizes Markdown files that define interfaces, API contracts, types and data shapes.

In plain words
What is it for?
Pulling the latest specifications, following them while coding, synchronizing approved changes and continuing with local specs if the server is unavailable.
Why use it?
It keeps agents working from the same definitions, reducing mismatched fields, incompatible APIs and merge conflicts.

Skill for Claude Code

Written for Claude Code: hooks in frontmatter. Also seen: reads .claude/ paths.

not rated 1repo 5mo ago A scan 100 tokens original MIT

Good fit Pulling the latest specifications, following them while coding, synchronizing approved changes and continuing with local specs if the server is unavailable.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shitianfang/coware-skills/coware
View source ↗ shitianfang/coware-skills
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.

Any agent
npx skills add shitianfang/coware-skills --skill coware
Clone the repo
git clone --depth 1 https://github.com/shitianfang/coware-skills

Made for: Claude Code.

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 coware

README.md
[![agentmods](https://agentmods.dev/badge/skills/shitianfang/coware-skills/coware/github.svg)](https://agentmods.dev/skills/shitianfang/coware-skills/coware)
Your own site
<a href="https://agentmods.dev/skills/shitianfang/coware-skills/coware"><img src="https://agentmods.dev/badge/skills/shitianfang/coware-skills/coware/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 coware

Your own site · 80×15
<a href="https://agentmods.dev/skills/shitianfang/coware-skills/coware"><img src="https://agentmods.dev/badge/skills/shitianfang/coware-skills/coware.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,372 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 $0.00100 $0.02372
Opus 5 $0.00050 $0.01186
Sonnet 5 $0.00020 $0.00474
Haiku 4.5 $0.00010 $0.00237

Measured 12d ago against content hash 86a8308346e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

coware 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 12d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/check-sync.mjs, scripts/pull-specs.mjs, scripts/validate-spec.mjs), 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.

coware/SKILL.md · 274 lines

How it starts

The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Coware — Shared Living Specs

Coware keeps AI agents aligned by syncing shared interface specs across your team. Every agent reads the same spec before writing code — no more merge conflicts from mismatched APIs, field names, or return types.

FIRST: Check initialization status

Check if .coware/config.json exists in the project root.

IF .coware/config.json EXISTS → Project is initialized

This project already uses Coware. Follow this workflow:

Before coding

  1. Run: node .coware/pull.mjs
    • This fetches the latest specs from the Coware server.
    • If the command fails (network error, server down), proceed with whatever local .coware/specs/*.md files exist.
  2. Read ALL .md files in .coware/specs/.
    • These specs are the source of truth for all interfaces, types, API contracts, and data shapes in this project.
  3. You are ready to code. Follow the specs exactly.

While coding

  • Follow specs exactly. Match field names, types, return formats, status codes.
  • If a spec needs to change (new endpoint, renamed field, etc.):
    1. Update the relevant .coware/specs/<slug>.md file FIRST.
    2. Run: node .coware/sync.mjs
    3. THEN update the code to match.
    4. Never let code drift from specs.

After coding

  1. If you created or modified any spec files, run: node .coware/sync.mjs
    • This pushes updated specs to the server so teammates get them.
    • If sync fails, the local spec files are still the source of truth.
  2. If you did NOT change any specs, no action needed.

IF .coware/config.json DOES NOT EXIST → New project setup

This project has not been initialized with Coware yet.

Setup instructions

  1. Fetch the setup guide: https://coware.team/llms.txt
  2. Read the response carefully.
  3. Follow ALL instructions in the guide from start to finish, in order.
    • The guide will walk you through: login, project creation/joining, file setup, and spec generation.
    • Execute ALL steps in ONE go. Do NOT stop to ask the user questions mid-flow.
    • The ONLY acceptable way to ask the user something is via a tool-based selection dialog. NEVER stop your turn to ask via text.
  4. After setup completes, follow the "Project is initialized" workflow above.

Read the full file on GitHub · 274 lines

Files

What ships with it

3 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. 12d ago First seen · 274 lines · 100 tokens per session scan A 86a8308346e6

Subscribe to this mod's changes

coware is a skill published in the GitHub repository shitianfang/coware-skills (1 stars, last pushed 5mo ago), licensed MIT. It adds 100 tokens to every session and 2,372 once invoked, about $0.0005 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.

Building agents
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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 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

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 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

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens