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/sijeeshmiziha/visionagentWrote 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/sijeeshmiziha/visionagent/coding-agents)<a href="https://agentmods.dev/rules/sijeeshmiziha/visionagent/coding-agents"><img src="https://agentmods.dev/badge/rules/sijeeshmiziha/visionagent/coding-agents/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/sijeeshmiziha/visionagent/coding-agents"><img src="https://agentmods.dev/badge/rules/sijeeshmiziha/visionagent/coding-agents.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 | $0.00348 | $0.00348 |
| Opus 5.5 | $0.00139 | $0.00139 |
| Sonnet 5.5 | $0.00070 | $0.00070 |
| Haiku 4.5 | $0.00035 | $0.00035 |
Grade A, and why
coding-agents 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.
What it actually says
Coding Agents
Prompt Pattern for Code Tasks
- Suggest a clear sequence in the prompt; do not hardcode the flow in code. Example: explore repo → reproduce the error (e.g. run a small script) → edit source → rerun to verify → consider edge cases.
- Keep the prompt concise; let the model choose how to move between steps. Optionally encourage longer reasoning if not token-sensitive.
Error-Proofing for File and Code-Editing Tools
- Paths: Prefer absolute paths for file/directory parameters so behavior is unambiguous after working-directory changes; avoid relative-path confusion.
- Edits: Prefer single-match string replace (
old_str→new_str) over full-file rewrites or diffs when the model must specify edits. Require exact match (including whitespace); on multiple or zero matches, return a clear error so the model can retry with more context. - Tool descriptions: Put environment and usage constraints in the description (e.g. no internet, state persistence, how to view files or line ranges, running long-lived commands in background). Test tools against real model outputs and fix recurring misuse in the spec.
Minimal Scaffolding
- Keep scaffolding minimal: give the model maximum control (e.g. one or two general-purpose tools like run-command + edit), and avoid hardcoded workflows. See agentic-patterns for simplicity and model-directed agents.
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 · 22 lines · 348 tokens per session scan A 92679ef49d12
coding-agents is a cursor rule published in the GitHub repository sijeeshmiziha/visionagent (2 stars, last pushed 7mo ago), licensed MIT. It adds 348 tokens to every session, about $0.0014 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
grug-brained-dev_simple-tools
Choose tools and libraries that are simple and well-understood.
160-workflow-orchestration
WHEN executing tasks MANAGE workflow processes for consistent memory operations.
080-creative-phase-metrics
description: WHEN entering a creative phase ENSURE comprehensive exploration and validation globs: ["/.md", "/.mdc"] alwaysApply: true.
050-reference-verification-system
description: WHEN referencing memory files ENSURE references are verified for accuracy and relevance globs: ["/.md", "/.mdc"] alwaysApply: true.
database
Cursor rule "database" from ItamarZand88/awesome-agent-conventions, covering database best practices, prisma setup, prisma models, prisma queries and supabase setup.
angular-typescript-cursorrules-prompt-file
description: "Cursor rules for Angular development with TypeScript integration." globs: / alwaysApply: false.