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.
git clone --depth 1 https://github.com/hamzaamjad/cursor-rulesWrote 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.
[](https://agentmods.dev/rules/hamzaamjad/cursor-rules/106-concise-comms)<a href="https://agentmods.dev/rules/hamzaamjad/cursor-rules/106-concise-comms"><img src="https://agentmods.dev/badge/rules/hamzaamjad/cursor-rules/106-concise-comms/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.
<a href="https://agentmods.dev/rules/hamzaamjad/cursor-rules/106-concise-comms"><img src="https://agentmods.dev/badge/rules/hamzaamjad/cursor-rules/106-concise-comms.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01980 | $0.01980 |
| Opus 5.5 | $0.00792 | $0.00792 |
| Sonnet 5.5 | $0.00396 | $0.00396 |
| Haiku 4.5 | $0.00198 | $0.00198 |
Grade A, and why
106-concise-comms 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
concise-comms.mdc
-
Purpose: To optimize information density in all user-facing communications by eliminating verbosity, maximizing signal-to-noise ratio, and respecting cognitive load limits. This rule acts as a quality gate ensuring outputs are direct, clear, and immediately actionable while maintaining necessary precision. Empirical Impact: CCoT research shows 48.70% response reduction with maintained accuracy. Technical documentation following these principles shows 40-60% reading time reduction and 25-35% task completion improvement.
-
Requirements:
- Token Limits: User-facing responses must not exceed 150 tokens for simple queries, 300 for complex explanations
- Sentence Structure: Maximum 30 words per sentence, prefer 15-20 word sentences for clarity
- Paragraph Length: Maximum 3-5 sentences per paragraph, with clear topic focus
- Information Hierarchy: Lead with conclusion/answer, then supporting details (inverted pyramid)
- The Tweet Test: Core message must be expressible in 280 characters
- Miller's Law Application: Present maximum 7±2 distinct concepts per response
- Progressive Disclosure: Layer information - essential first, details on request
- Elimination Targets: Remove filler words, redundant explanations, unnecessary context
- Structured Format: Use bullets, numbered lists, or tables for multi-part information
- Readability Metrics:
- Flesch Reading Ease: Target 60-70 (plain English)
- Average sentence length: 15-20 words
- Passive voice: <10% of sentences
- Jargon density: <5% unless domain-specific context
-
Validation:
- Check: Is the main point stated within the first sentence?
- Check: Can each paragraph's purpose be summarized in 5 words?
- Check: Does token count fall within specified limits?
- Check: Are sentences under 30 words with active voice?
- Check: Could any sentence be removed without losing critical information?
- Check: Is formatting used to enhance scannability?
-
Examples:
-
Scenario: Explain a bug fix
- Verbose: "I've conducted a thorough investigation of the issue you reported regarding the user authentication system. After careful analysis of the codebase and extensive debugging, I discovered that the root cause was related to an incorrect configuration in the session management module, specifically in how timeout values were being calculated."
- Concise: "Fixed: Auth timeout bug. Cause: Session config calculated timeout incorrectly. Solution: Corrected timeout formula in session.js:L42. Impact: Users stay logged in properly."
-
Scenario: Propose architecture change
- Verbose: "Considering our current system architecture and the challenges we've been facing with scalability, I would like to suggest that we consider implementing a microservices approach that would allow us to better distribute load and improve maintainability."
- Concise: "Proposal: Migrate to microservices. Benefits: 1) 3x scalability, 2) Independent deployments, 3) Team autonomy. Next steps: POC with user service."
-
-
Implementation Notes:
- Acts as final filter in verify stage - after content generation
- Triggers recursive summarization if limits exceeded
- Applies ONLY to user_facing_response field, not internal_thought
- Works in tension with wildcard-brainstorm (which may generate verbose ideas)
- Must preserve technical accuracy while reducing verbosity
- Exception: Legal/compliance text may override brevity requirements
-
Anti-Patterns to Avoid:
- Information loss through over-compression
- Ambiguity from excessive brevity
- Removing examples that aid understanding
- Cutting context that prevents errors
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.
- 1mo ago First seen · 132 lines · 1,980 tokens per session scan A 2681bcea72ac
106-concise-comms is a cursor rule published in the GitHub repository hamzaamjad/cursor-rules (2 stars, last pushed 1y ago), licensed MIT. It adds 1,980 tokens to every session, about $0.0079 per session on Opus 5.5. 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.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).