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/context-engineering)<a href="https://agentmods.dev/rules/sijeeshmiziha/visionagent/context-engineering"><img src="https://agentmods.dev/badge/rules/sijeeshmiziha/visionagent/context-engineering/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/context-engineering"><img src="https://agentmods.dev/badge/rules/sijeeshmiziha/visionagent/context-engineering.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 | $0.00377 | $0.00377 |
| Opus 5.5 | $0.00151 | $0.00151 |
| Sonnet 5.5 | $0.00075 | $0.00075 |
| Haiku 4.5 | $0.00038 | $0.00038 |
Grade A, and why
context-engineering 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
Context Engineering for Agents
Context Is Finite
- Treat the context window as a scarce resource with diminishing returns; every token consumes attention budget.
- Aim for the smallest high-signal set of tokens that maximizes the chance of the desired outcome.
System Prompts
- Right altitude: Specific enough to guide behavior, flexible enough for heuristics. Avoid brittle if-else logic in prompts or vague, high-level hand-waving.
- Organize prompts with clear sections (e.g. XML tags or Markdown headers like
## Tool guidance,## Output description). Keep them minimal but sufficient.
Just-in-Time Context
- Prefer lightweight references (file paths, stored queries) and load data on demand via tools instead of pre-loading everything.
- Use progressive disclosure: let the agent discover and load only what it needs for the current step.
Compaction and Long Horizons
- When context nears limits: summarize and compress; clear old tool call results; preserve architectural decisions and unresolved issues.
- Use structured note-taking: agents write persistent notes (e.g.
NOTES.md, progress files) outside the context window for cross-session memory.
Sub-Agent Architectures
- Use focused sub-agents with clean context windows for deep work (e.g. research, code cleanup).
- Sub-agents should return condensed summaries (on the order of 1–2k tokens) to the lead agent; keep detailed context isolated.
- For orchestration, delegation, scaling effort, and production patterns, see the multi-agent-systems rule.
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 · 33 lines · 377 tokens per session scan A 85fed357344e
context-engineering is a cursor rule published in the GitHub repository sijeeshmiziha/visionagent (2 stars, last pushed 7mo ago), licensed MIT. It adds 377 tokens to every session, about $0.0015 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
wrapup
End-of-session wrap-up: summarizes the session and pushes a log to the project's linked NotebookLM notebook. Activate with @wrapup in chat, or "wrap up", "save this session", or "end of session".
160-workflow-orchestration
WHEN executing tasks MANAGE workflow processes for consistent memory operations.
170-protocol-enforcement-mechanisms
description: WHEN executing commands ENFORCE protocol compliance for memory bank operations globs: ["/.md", "/.mdc"] alwaysApply: true.
130-validation-reporting-system
description: WHEN verification completes GENERATE comprehensive reports on memory bank health globs: ["/.md", "/.mdc"] alwaysApply: true.
140-unified-command-interface
WHEN processing commands APPLY unified interface patterns for consistent memory bank operations.
150-standard-initialization-procedure
WHEN starting a new session EXECUTE initialization procedure to establish memory context.