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/CiscoDevNet/essentialsWrote 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/ciscodevnet/essentials/write-readme)<a href="https://agentmods.dev/rules/ciscodevnet/essentials/write-readme"><img src="https://agentmods.dev/badge/rules/ciscodevnet/essentials/write-readme.svg" alt="Measured on agentmods" 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 | $0.00422 | $0.00422 |
| Opus 5 | $0.00211 | $0.00211 |
| Sonnet 5 | $0.00084 | $0.00084 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
write-readme 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.
What it actually says
How to Write a README
When writing or updating a README, follow this framework in order. A reader should be able to answer two questions quickly: "Does this solve my problem?" and "How do I use it?"
1. Example First
Start with a short, runnable code snippet that shows the most common use case. The reader should be able to infer how the project works from this example alone.
- Show what the project does, not how it's built.
- Keep it minimal — one common use case, not the full API.
- A one-line description before the example (e.g., "Like
mkdir -p, but in node.js!") adds important context.
2. Installation
Provide copy-pasteable install commands. Aim for a one- or two-liner. If the procedure is complex, break it into numbered steps — don't leave the reader guessing.
3. API / Usage
Document the main entry points. Start with the most obvious one and work outward.
- Name each function/class/command with its signature.
- Describe each parameter: type, whether it's required or optional, and what it does.
- Don't rely solely on the example for this — be explicit.
4. Running Tests
If the project has tests, state how to run them in a single command (e.g., npm test, pytest). Mention what framework is used and what the tests cover.
5. License
A short mention is fine (e.g., "MIT"). Link to the full LICENSE file if one exists.
6. Stay Focused
A README answers "What is it?" and "How do I use it?" — nothing more. Keep design rationale, architecture deep-dives, and opinions out of the README. Link to separate docs, ADRs, or blog posts for that content.
Sources
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.
- 2d ago First seen · 45 lines · 422 tokens per session scan A b378716240c5
write-readme is a cursor rule published in the GitHub repository CiscoDevNet/essentials (7 stars, last pushed 18d ago), licensed Apache-2.0. It adds 422 tokens to every session, about $0.0021 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 2026-09-04.
Other cursor rules, from other repositories
solar
Rules for building with Solar (solarbuild) — a runtime UI framework for AI-generated code.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
as-contract-cast-smell
// ❌ WRONG — bypasses the family ContractSerializer seam const contract = JSON.parse(raw) as Contract; const contract = JSON.parse(raw) as Contract .
no-family-vocabulary-in-framework
The framework domain (packages/1-framework) carries no family- or target-specific vocabulary — types, fields, hooks, or strategy values. Enforced by the no-family-vocabulary Biome plugin plus lint:framework-vocabulary.
use-contract-ir-factories
Use factory functions for creating ContractIR objects instead of manual object creation.
no-barrel-files
Avoid barrel files and unnecessary re-exports.