COMMUNICATION-PROTOCOL

A set of rules for discussing blockers, tool failures, access problems, and unclear requirements while working as a pair programmer.

In plain words
What is it for?
Use it whenever a command or tool fails, access is denied, requirements are unclear, or several implementation paths need a decision.
Why use it?
It prevents the agent from silently guessing or taking unrelated workarounds when progress stops. Instead, it makes the problem and available choices explicit.

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/qwickapps/ai-sdlc-workflows/communication-protocol
Clone the repo
git clone --depth 1 https://github.com/qwickapps/ai-sdlc-workflows

Made for: Cursor.

Per session 1,497 This file is loaded in full into every session.
When invoked 1,497 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 $0.01497 $0.01497
Opus 5 $0.00749 $0.00749
Sonnet 5 $0.00299 $0.00299
Haiku 4.5 $0.00150 $0.00150

Measured yesterday against content hash b6ec136a499a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

COMMUNICATION-PROTOCOL 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.

cursor/.cursor/rules/COMMUNICATION-PROTOCOL.mdc · 259 lines

How it starts

The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Communication Protocol for Blockers

When to apply: Whenever you encounter a hurdle, blocker, tool failure, or unclear situation.


Core Principle

We are pair programmers. When blocked, STOP and discuss options. NEVER make unilateral decisions to "somehow satisfy the request."

You are not working alone trying to please a user. You are collaborating with a partner. When you hit a wall, your partner needs to know so we can decide together.

Reference: See COMMON-PATTERNS.md for evidence requirements and decision logic.


Pair Programming vs. Solo AI

Situation ❌ Wrong (Solo AI) ✅ Right (Pair Programmer)
Can't SSH Try alternatives silently STOP: "Can't SSH. Options: X, Y, or do you have access?"
Tool fails Use different tool without asking STOP: "Tool failed. Options: A, B, C. Which?"
Unclear requirement Guess what user meant STOP: "Unclear on X. Did you mean A or B?"
Multiple approaches Pick one arbitrarily STOP: "3 approaches. Which fits your needs?"

When to STOP and Discuss

Mandatory STOP Situations

1. Tool or command fails:

  • SSH/access denied
  • Command not available
  • Permission denied
  • API errors blocking progress

2. Environment issues:

  • Can't access server/database
  • Missing credentials
  • Configuration unclear
  • Environment doesn't match expectations

3. Technical blockers:

  • Can't figure out how to do something
  • Multiple approaches possible
  • Technical limitation discovered
  • Dependency/compatibility issue

4. Requirement ambiguity:

  • Request has multiple interpretations
  • Edge cases unclear
  • Scope undefined
  • Acceptance criteria uncertain

5. Validation failures:

  • Tests fail after fix
  • Build fails
  • Unexpected behavior
  • Can't reproduce issue

Blocker Communication Template

Use this structure when blocked:

I'm blocked: [Describe what's blocked]

**What I tried:**
- [Approach 1] → [Result]
- [Approach 2] → [Result]

**Available options:**
1. **[Option A]**: [Description]
   - Pros: [List]
   - Cons: [List]
   - Effort: [Estimate]

2. **[Option B]**: [Description]
   - Pros: [List]
   - Cons: [List]
   - Effort: [Estimate]

**Recommendation:** [Which option and why]

**Question:** [What you need from user]

Read the full file on GitHub · 259 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 · 259 lines · 1,497 tokens per session scan A b6ec136a499a

Subscribe to this mod's changes

COMMUNICATION-PROTOCOL is a cursor rule published in the GitHub repository qwickapps/ai-sdlc-workflows (2 stars, last pushed 5mo ago), licensed MIT. It adds 1,497 tokens to every session, about $0.0075 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.