Council
affaan-m/ECC
Convene a four-voice council for ambiguous decisions, tradeoffs, and go/no-go calls.
Run five independent reasoners on one high-stakes decision and converge.
AGPL-3.0Auto-check passed
Install Council Of Five
$ npx skills add Inebrio/Routerly --skill council-of-five -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Inebrio/Routerly council-of-five --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Inebrio/Routerly.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/council-of-five .claude/skills/council-of-five && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "council-of-five" agent skill from https://github.com/Inebrio/Routerly/tree/develop/.agents/skills/council-of-five into .claude/skills/council-of-five/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "council-of-five", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Inebrio/Routerly/tree/develop/.agents/skills/council-of-fiveType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Inebrio/Routerly --skill council-of-five -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Inebrio/Routerly council-of-five --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Inebrio/Routerly.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/council-of-five .agents/skills/council-of-five && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "council-of-five" agent skill from https://github.com/Inebrio/Routerly/tree/develop/.agents/skills/council-of-five into .agents/skills/council-of-five/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "council-of-five", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Inebrio/Routerly --skill council-of-five -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Inebrio/Routerly council-of-five --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Inebrio/Routerly.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/council-of-five .cursor/skills/council-of-five && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "council-of-five" agent skill from https://github.com/Inebrio/Routerly/tree/develop/.agents/skills/council-of-five into .cursor/skills/council-of-five/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "council-of-five", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Inebrio/Routerly.git --path .agents/skills/council-of-five--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Inebrio/Routerly --skill council-of-five -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Inebrio/Routerly council-of-five --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Inebrio/Routerly.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/council-of-five .gemini/skills/council-of-five && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "council-of-five" agent skill from https://github.com/Inebrio/Routerly/tree/develop/.agents/skills/council-of-five into .gemini/skills/council-of-five/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "council-of-five", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Inebrio/Routerly council-of-fiveInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Inebrio/Routerly --skill council-of-five -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Inebrio/Routerly.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/council-of-five .github/skills/council-of-five && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "council-of-five" agent skill from https://github.com/Inebrio/Routerly/tree/develop/.agents/skills/council-of-five into .github/skills/council-of-five/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "council-of-five", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Inebrio/Routerly --skill council-of-five -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Inebrio/Routerly council-of-five --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Inebrio/Routerly.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/council-of-five .opencode/skills/council-of-five && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "council-of-five" agent skill from https://github.com/Inebrio/Routerly/tree/develop/.agents/skills/council-of-five into .opencode/skills/council-of-five/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "council-of-five", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
council-of-five- GitHub stars
- 101
- Token cost
- ~641 tokens
- SKILL.md length
- 404 words
- Files
- 1
- Skills in repo
- 17
- Repo updated
- First seen
- Licence
- AGPL-3.0
At a glance
Run five independent reasoners on one high-stakes decision and converge.
- Works in 5 steps: Correctness — does it actually do what… → Simplicity — what is the smallest thing… → Risk — how does this fail in production,… → …
- A choice is expensive to reverse and a single opinion is not enough
- SKILL.md covers When, The lenses, Procedure and Output
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Council Of Five is an agent skill from Inebrio/Routerly. Run five independent reasoners on one high-stakes decision and converge. Use when a choice is expensive to reverse and a single opinion is not enough.
Its SKILL.md is about 640 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: Self-hosted LLM gateway that routes requests across AI providers (OpenAI, Anthropic, Gemini, Mistral, Ollama) using intelligent multi-policy scoring — including an LLM-native… The licence is AGPL-3.0.
When your agent uses it
- A choice is expensive to reverse and a single opinion is not enough
Example prompts
- “/council-of-five”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Correctness — does it actually do what is asked, in every branch and
- Simplicity — what is the smallest thing that works, and what here is
- Risk — how does this fail in production, what data can be lost, what
- Fit — does it match what this codebase already does, or does it
- Future cost — who pays for this in six months, at change time and at
What it can do on your machine
Read from SKILL.md and the folder at commit bcf58f1. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Council Of Five loads about 641 tokens when it runs. Until then it costs about 42 tokens; SKILL.md has 404 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from Inebrio/Routerly at commit bcf58f1, republished under its AGPL-3.0 licence (© Inebrio). 404 words, ~641 tokens.
Download SKILL.mdSave it as
.claude/skills/council-of-five/SKILL.md (or your agent's skills folder).- name
- council-of-five
- description
- Run five independent reasoners on one high-stakes decision and converge. Use when a choice is expensive to reverse and a single opinion is not enough.
Council of five
Five agents reason on the same question independently, then read each other and converge. Independence is the whole mechanism: five agents given the same prompt agree trivially and prove nothing, so each gets a different lens.
When
Only for decisions that are expensive to reverse: architecture, a data model, a public contract, a security boundary, a migration, a choice between two designs the analysis could not settle. Five agents cost five times one. A decision you can undo in an hour is not worth it.
The lenses
Each council member gets the same question, the same artifacts, and one of:
- Correctness — does it actually do what is asked, in every branch and edge case?
- Simplicity — what is the smallest thing that works, and what here is not needed?
- Risk — how does this fail in production, what data can be lost, what is the blast radius?
- Fit — does it match what this codebase already does, or does it introduce a second way to do the same thing?
- Future cost — who pays for this in six months, at change time and at debug time?
Show full SKILL.md (214 more words)Show less
Procedure
Round 1, blind. Spawn all five in parallel. Each returns: a verdict, the three strongest reasons for it, and the strongest argument against its own position. No member sees another's output.
Converge. Count verdicts.
- Four or five agree → adopt it. Record the dissent in one line: it is the first thing to check if the decision goes wrong.
- Three or fewer → run round 2.
Round 2, informed. Give every member all five round-1 outputs and ask one question: which position survives, and what would have to be true for you to be wrong? Members may change their verdict, and changing it on a good argument is the point, not a failure.
Converge again. Four or more agree → adopt. Otherwise stop.
Cap: two rounds. A council that has not converged twice will not converge on the third try: it has found a real trade-off, not a wrong answer. Escalate to the human with both positions stated fairly, what each one costs, and which one you would take.
Output
Write the decision where the work will look for it, in the analysis or the blueprint: what was decided, on what reasoning, what the dissent said, and what evidence would overturn it. A decision nobody can find is a decision that gets made again next week.
© Inebrio, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .agents/skills/council-of-five of Inebrio/Routerly.
Open the folder on GitHubat commit bcf58f1
Compare with similar skills
Council Of Five next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Council Of Five this skillInebrio/Routerly | 101 | — | ~641 | Automated safety check: Pass | AGPL-3.0 | |
| Councilaffaan-m/ECC | 277k | 2 repos | ~1.6k | Automated safety check: Pass | MIT | |
| Councilaffaan-m/ECC | 276k | — | ~963 | Automated safety check: Pass | MIT | |
| Councilaffaan-m/ECC | 276k | — | ~653 | Automated safety check: Pass | MIT | |
| Council0xNyk/council-of-high-intelligence | 4.6k | 1 repos | ~14k | Automated safety check: Pass | MIT | |
| Council External Codex Reviewaffaan-m/ECC | 277k | — | ~1.5k | Automated safety check: Pass | MIT |
Similar skills
Council
affaan-m/ECC
曖昧な決定、トレードオフ、ゴー/ノーゴーの判断のために4つの声のカウンシルを召集します。複数の有効なパスが存在し、選択前に構造化された異議が必要な場合に使用します。
Council
affaan-m/ECC
召集四方会议处理模糊决策、权衡取舍及继续/停止决策。当存在多个有效路径且需要在选择前进行结构化异议时使用. An agent skill from affaan-m/ECC.
Council
0xNyk/council-of-high-intelligence
Convene the Council of High Intelligence — multi-persona deliberation with historical thinkers for deeper analysis of complex problems.
Council External Codex Review
affaan-m/ECC
Adds one optional external Codex critique that tries to break a council's decision draft, sent to OpenAI only after you consent.
Consciousness Council
K-Dense-AI/scientific-agent-skills
Structures a multi-perspective council exercise for decisions, research trade-offs, and creative challenges.
More from Inebrio/Routerly
All 17 skills in this repoDocs Conventions
Inebrio/Routerly
Where documentation lives in this repository, how a page is structured, and what a change owes the docs.
Feature Lifecycle
Inebrio/Routerly
Run a Tier 1 or Tier 2 feature end to end — feature level, story level, parallelism, integration, and retrospective.
Story Lifecycle
Inebrio/Routerly
Run one user story end to end in its own worktree, from claim to merge.
Test Conventions
Inebrio/Routerly
Where tests live in this repository, how to run them, and what a story owes in coverage.
Validation Protocol
Inebrio/Routerly
How to validate a story against its criteria and write the report, including what counts as evidence and what counts as blocking.
Analysis Format
Inebrio/Routerly
Shape of a feature analysis document (00-analysis.md). An agent skill from Inebrio/Routerly.
Questions about Council Of Five
What does Council Of Five do?
Run five independent reasoners on one high-stakes decision and converge. Council Of Five is an agent skill from Inebrio/Routerly. Run five independent reasoners on one high-stakes decision and converge.
When should I use Council Of Five?
Council Of Five fits situations like: A choice is expensive to reverse and a single opinion is not enough.
How do I install Council Of Five in Claude Code?
Run `npx skills add Inebrio/Routerly --skill council-of-five -a claude-code`. Or copy the skill folder (.agents/skills/council-of-five in Inebrio/Routerly) into .claude/skills/council-of-five in your project. Claude Code loads it when a task matches its description.
How do I install Council Of Five in Codex?
Run `npx skills add Inebrio/Routerly --skill council-of-five -a codex`. Or copy the skill folder (.agents/skills/council-of-five in Inebrio/Routerly) into .agents/skills/council-of-five in your project. Codex loads it when a task matches its description.
Can I use Council Of Five in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Inebrio/Routerly --skill council-of-five -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/council-of-five, .gemini/skills/council-of-five, .github/skills/council-of-five and .opencode/skills/council-of-five in your project.
What does Council Of Five need to run?
SKILL.md names no scripts, command-line tools or credentials: Council Of Five is instructions for the agent only.
Does Council Of Five access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Council Of Five safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Council Of Five use?
Council Of Five is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Council Of Five use?
About 641 tokens (SKILL.md is roughly 2.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Council Of Five?
Skills that share tags, products or a category with Council Of Five: Council (affaan-m/ECC, 277k stars), Council (affaan-m/ECC, 276k stars), Council (affaan-m/ECC, 276k stars) and Council (0xNyk/council-of-high-intelligence, 4.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Council Of Five?
Inebrio (a GitHub organization) maintains it in Inebrio/Routerly, which has 101 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 8, 2026.
Source: Inebrio/Routerly on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.