collaboration

Rules for how an AI coding assistant should communicate and make code changes. They emphasize concise communication, readable code, preserving behavior, and test-first bug fixes.

In plain words
What is it for?
Guiding collaboration, refactoring, architectural discussions, and a red-green test-driven development workflow, where a failing test is written before the fix.
Why use it?
They give the assistant consistent working habits, including explaining decisions briefly and checking changes with tests.

Cursor rule for Cursor

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 rules/kanyun-inc/reskill/collaboration
Clone the repo
git clone --depth 1 https://github.com/kanyun-inc/reskill

Made for: Cursor.

Per session 473 This file is loaded in full into every session.
When invoked 473 The same file — it is already loaded in full.
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 $0.00473 $0.00473
Opus 5 $0.00236 $0.00236
Sonnet 5 $0.00095 $0.00095
Haiku 4.5 $0.00047 $0.00047

Measured 2d ago against content hash 599b252f6df7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

collaboration 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.

.cursor/rules/collaboration.mdc · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Collaboration Preferences

Communication Style

  • Be direct and concise, skip unnecessary pleasantries
  • When proposing changes, explain the "why" briefly before the "how"
  • If uncertain about intent, ask a focused question rather than guessing

Coding Expectations

  • Write clean code from the first attempt: no ugly callbacks, no inline logic
  • Extract functions, name clearly, single responsibility
  • Prefer readability over cleverness
  • When refactoring, preserve existing behavior unless explicitly asked to change it

Decision Making

  • When multiple approaches exist, briefly present trade-offs and recommend one
  • For small decisions, just pick the better option and explain why
  • For architectural decisions, switch to Plan mode to discuss

Workflow Preferences

  • Don't create files unless absolutely necessary; prefer editing existing ones
  • Run tests after meaningful changes to catch regressions early
  • When fixing bugs, strictly follow TDD RED-GREEN cycle:
    1. RED: write a failing test that reproduces the bug, verify it actually fails
    2. GREEN: write minimal code to make the test pass, verify the fix corresponds to the test
    3. Never skip the RED step — a test that never failed proves nothing
    4. After fix: build and run node dist/cli/index.js <command> to manually verify the actual CLI behavior matches expectations
  • Commit only when explicitly asked
  • Before creating a commit, always check:
    1. Changeset: If the change affects public behavior (bug fix / feature / breaking), create a changeset file in .changeset/ following the bilingual format in development.mdc
    2. README: If CLI command behavior, options, or output changed, check if README.md needs updating
    3. Docs: If the change introduces new concepts or modifies architecture, check if docs/ or CLAUDE.md need updating

What I Value

  • Accuracy over speed: double-check before answering
  • Consistency: follow existing patterns in the codebase
  • Proactive suggestions: if you notice something off, mention it
  • Context awareness: remember what we discussed in this session

Read the full file on GitHub · 48 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. 2d ago First seen · 48 lines · 473 tokens per session scan A 599b252f6df7

Subscribe to this mod's changes

collaboration is a cursor rule published in the GitHub repository kanyun-inc/reskill (59 stars, last pushed 21d ago), licensed MIT. It adds 473 tokens to every session, about $0.0024 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.