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/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/headroom)<a href="https://agentmods.dev/rules/oriolshhh/runware-image-mcp/headroom"><img src="https://agentmods.dev/badge/rules/oriolshhh/runware-image-mcp/headroom/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/oriolshhh/runware-image-mcp/headroom"><img src="https://agentmods.dev/badge/rules/oriolshhh/runware-image-mcp/headroom.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 | $0.00007 | $0.00313 |
| Opus 5.5 | $0.00003 | $0.00125 |
| Sonnet 5.5 | $0.00001 | $0.00063 |
| Haiku 4.5 | $0.00001 | $0.00031 |
Grade A, and why
headroom 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
Pack: headroom (enabled)
This pack is enabled; its guidance is composed into the core rule.
Pack: Headroom
Behavioral goal
Summarize noisy logs and large outputs without losing any fact needed to act.
Rules
- Preserve exact failures, commands, filenames, line numbers, and assertions.
- Preserve API changes, risks, and decisions verbatim.
- Distinguish observed facts, inferences, and uncertainty; note what was omitted.
Priorities
Default-on, priority 30.
Boundaries
Compresses communication only; never drops information needed to continue.
Possible conflicts
None expected; complements every other pack.
Enable when / avoid when
- Keep enabled for long tool output, logs, and multi-step work.
- Temporarily avoid only when the user explicitly requests a complete transcript.
Observable effect
Repeated output is summarized, exact failures remain quoted, and the response states what was omitted plus the next actionable step.
Never override
Correctness, safety, repository conventions, or explicit user instructions.
Apply
context-discoverybefore broad scanning: use a supplied context capsule first; otherwise check context frontmatter freshness, read.agent/context/routing.md, load only relevant summaries, and verify critical claims against source.
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 · 44 lines · 7 tokens per session scan A 010fc8520876
headroom is a cursor rule published in the GitHub repository Oriolshhh/runware-image-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 7 tokens to every session and 313 once invoked, about $0.0000 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 2026-09-03.
Other cursor rules, from other repositories
e2e-testing
E2E Flow Tests setup and debugging guide.
review-agent-config
Diagnostic gate that checks CLAUDE.md and AGENTS.md for completeness, consistency, and stale artifacts — run right after /cold-start and before /add-feature. Read-only; produces a findings report.
fix-bug
Fix a bug using the knowledge layer — reproduce first, failing regression test, root cause, surgical fix, review and ledger entry after.
search-safety
Use bounded searches (headlimit, path scope); exhaust search methods before concluding 'not found'. Don't retry the exact same search.
vscode
VS Code: settings, extensions, workspace config.
kiss-ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.