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.
npx agentmods add rules/oriolshhh/runware-image-mcp/context-discoverygit clone --depth 1 https://github.com/Oriolshhh/runware-image-mcpWrote 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/oriolshhh/runware-image-mcp/context-discovery)<a href="https://agentmods.dev/rules/oriolshhh/runware-image-mcp/context-discovery"><img src="https://agentmods.dev/badge/rules/oriolshhh/runware-image-mcp/context-discovery.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 | $0.00012 | $0.00744 |
| Opus 5 | $0.00006 | $0.00372 |
| Sonnet 5 | $0.00002 | $0.00149 |
| Haiku 4.5 | $0.00001 | $0.00074 |
Grade A, and why
context-discovery 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: context-discovery
Context Discovery
Purpose
Orient an agent from previously built repository context before spending time and tokens rediscovering architecture, locations, commands, and conventions.
When to use it
- At the start of a session when the repository or affected subsystem is unfamiliar.
- Before broad file searches, architecture decisions, debugging across modules, security review, or changes that cross boundaries.
- When another agent hands off work with
.agent/context/available.
Instructions
- Check for
.agent/context/README.mdand.agent/context/routing.mdbefore broadly scanning the repository. - Read their frontmatter first. Compare
repository_revision,scope, andupdated_atwith the current task and repository revision when available. - Use
routing.mdto select only the relevant context documents; do not load the whole pack automatically. - Build a short working orientation: likely modules/files, runtime flow, conventions, tests, commands, risks, and explicit unknowns for this task. When coordinating subagents, turn this into one context capsule containing the context revision, task scope, relevant summary facts, exact source paths, constraints, risks, and unknowns. Send the same capsule with each delegation.
- Verify critical or change-sensitive claims against cited source before editing. Context is a navigation aid, not higher authority than the repository.
- If context is missing, materially stale, out of scope, contradictory, or lacks
evidence, invoke
/build-contextwith a targeted refresh scope before broad work. - Preserve useful discoveries by refreshing the affected context documents when the task changes architecture, routing, commands, data, or conventions.
- A subagent receiving a fresh context capsule must start from that capsule. It should not reopen the entire context pack or broadly scan the repository; read only a cited summary/source needed to resolve a concrete gap or verify a change-sensitive claim.
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 · 73 lines · 12 tokens per session scan A 6bab99665c57
context-discovery is a cursor rule published in the GitHub repository Oriolshhh/runware-image-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 744 once invoked, about $0.0001 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 2026-09-03.
Other cursor rules, from other repositories
reflection-basic
Basic reflection format for Level 2 Simple Enhancement tasks.
cursor-fable-rules
Fable coding lifecycle discipline and situational awareness for Cursor.
git-workflow
Rules for git operations, commit strategy, and GitHub CLI usage.
feedback-enhanced
Enhanced feedback mechanism with 1-hour timeout - 增强反馈机制，1小时超时.
122-swift-development
122: Swift development workflow including TDD, refactoring, and performance optimization.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.