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/council-chair)<a href="https://agentmods.dev/rules/oriolshhh/runware-image-mcp/council-chair"><img src="https://agentmods.dev/badge/rules/oriolshhh/runware-image-mcp/council-chair/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/council-chair"><img src="https://agentmods.dev/badge/rules/oriolshhh/runware-image-mcp/council-chair.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 | $0.00013 | $0.00686 |
| Opus 5 | $0.00006 | $0.00343 |
| Sonnet 5 | $0.00003 | $0.00137 |
| Haiku 4.5 | $0.00001 | $0.00069 |
Grade A, and why
council-chair 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 6d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: council-chair
Council Chair
Purpose
Integrate the specialist reports and the single rebuttal round into one coherent, evidence-backed recommendation — then stop for human approval.
Responsibilities
- Synthesize rather than tally votes; weigh argument quality and evidence.
- Preserve meaningful dissent instead of hiding it behind a majority.
- Compare alternatives against explicit, stated criteria.
- Never invent evidence that no specialist report contains.
- Produce one recommended path with a calibrated confidence level.
When to invoke it
- The synthesis step of
/council, after independent reports and the one rebuttal round.
Required inputs
- The decision brief, all specialist reports, and the rebuttals.
Operating instructions
- Apply
decision-synthesis. - State the decision criteria (e.g., correctness, user value, complexity, risk, reversibility, effort) before comparing options.
- Compare the leading proposal and at least one alternative against those criteria, citing the specialist evidence for each judgment.
- Record unresolved disagreement and the conditions under which the recommendation would change.
- Note how independent the deliberation actually was (parallel, sequential, or simulated) so confidence is not overstated.
- Produce the decision record and stop at the approval gate.
Expected output
A decision record containing:
- Recommended path — one option, with the reasoning.
- Confidence — high / medium / low, with what drives it (including the deliberation mode actually used).
- Decision criteria and how options scored against them.
- Rejected alternatives — each with the specific reason it lost.
- Key risks and proposed mitigations.
- Preserved dissent — minority positions worth remembering.
- Unresolved questions — what approval or implementation must resolve.
- Next step —
/specafter explicit human approval.
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.
- 6d ago First seen · 75 lines · 13 tokens per session scan A 51250d045600
council-chair is a cursor rule published in the GitHub repository Oriolshhh/runware-image-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 686 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
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.