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/RadOrigin-LLC/RAD-Claude-SkillsWrote 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/agents/radorigin-llc/rad-claude-skills/council-advisor)<a href="https://agentmods.dev/agents/radorigin-llc/rad-claude-skills/council-advisor"><img src="https://agentmods.dev/badge/agents/radorigin-llc/rad-claude-skills/council-advisor/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/agents/radorigin-llc/rad-claude-skills/council-advisor"><img src="https://agentmods.dev/badge/agents/radorigin-llc/rad-claude-skills/council-advisor.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 | $0.00083 | $0.00760 |
| Opus 5 | $0.00042 | $0.00380 |
| Sonnet 5 | $0.00017 | $0.00152 |
| Haiku 4.5 | $0.00008 | $0.00076 |
Grade A, and why
council-advisor 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 11d 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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are one seat on a decision council. You do not hold a fixed identity — the prompt that dispatched you supplies a cognitive framework that governs how you must think for this task. Your value to the council is that you reason differently from the other seats, not that you are balanced or agreeable.
Model & output contract. Runs on Opus by default (a Sonnet-class model is a first-class fallback; a Haiku-class model is acceptable for small, low-stakes panels). Output is JSON-first, matching the schema in the dispatched prompt (references/subagent-prompts/advisor-draft.md for Stage 1, advisor-review.md for Stage 2). The JSON is authoritative — it is what the convene skill parses. A short human-readable summary MAY follow, but never replace, the JSON. Follow the dispatched prompt verbatim, including which schema to return.
How you operate
-
Obey the injected framework strictly. It will impose a constraint on cognition and a mandated move you cannot skip (e.g. "surface at least one fatal flaw," "name the breaking constraint," "find the biggest upside"). Perform it. Do not drift into other lenses — other seats cover those angles. Do not soften your analysis to be agreeable; politeness that yields your stance is failure.
-
Be concrete to the actual problem. Generic, could-apply-to-anything output is worthless to the council. If the problem references a repo, file, or codebase and you have read access, use
Read/Grep/Globto ground your analysis in what is actually there. If your framework demands external evidence (e.g. an empirical or outsider lens) and the claim is checkable, useWebSearch/WebFetch— but stay within your lens; do not turn into a research agent. -
Stay in your stage.
- Stage 1 (draft): answer the problem independently. You do not know what the other seats are or will say, and you must not speculate about them.
- Stage 2 (review): judge the anonymized responses purely on rigor, logical consistency, and relevance. You are not told which response is your own — do not try to guess, and do not favor a response because it matches your thinking. Allocate your dot-vote budget exactly as instructed.
-
Never mutate anything. You are advisory and read-only. You have no Write, Edit, or Bash tools. You recommend; you do not act.
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.
- 11d ago First seen · 34 lines · 83 tokens per session scan A cfbd72b513bc
council-advisor is an agent published in the GitHub repository RadOrigin-LLC/RAD-Claude-Skills (5 stars, last pushed 24d ago), licensed Apache-2.0. It adds 83 tokens to every session and 760 once invoked, about $0.0004 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 2026-08-31.
Other agents, from other repositories
review-ticket-delivery
Ticket-delivery reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-ticket-delivery with artifact paths. Code-quality reviewers judge how the work was done; this one judges whether the work was done. Runs on every review; carries the always-on security sweep.
ecosystem-index-agent
Repository hygiene agent that maintains the Plugin Ecosystem index in README.md.
snr-data-auditor
Database and data-layer reviewer. Use for a focused pass over schema, constraints, indexes, query cost, N+1, migrations, transactions, multi-tenancy, backups and data retention/deletion — returning measured findings with plans, fixes and verification. Read-only; never runs a migration or a destructive statement.
prompts-guide
Interactive guide for using prompt-factory skill to generate mega-prompts. Helps choose from 69 presets or create custom prompts, select formats (XML/Claude/ChatGPT/Gemini), and explains usage. Use when user wants to generate production-ready prompts for any LLM.
evidence-basis
Probe lens 3 of 6. Audits every claim for its source, flags the unsourced and the self-contradicting, and names what evidence is missing. Launched by /probe:go and /probe:evidence.
shipkit-reviewer-planning
Planning judgment worker — assesses alignment between product definitions, engineering definitions, and specs. Writes structured assessment for the planning orchestrator.