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 skills/yogirk/agent-council/claude-codenpx skills add yogirk/agent-council --skill claude-codegit clone --depth 1 https://github.com/yogirk/agent-councilWrote 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/skills/yogirk/agent-council/claude-code)<a href="https://agentmods.dev/skills/yogirk/agent-council/claude-code"><img src="https://agentmods.dev/badge/skills/yogirk/agent-council/claude-code.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 | $0.00067 | $0.00955 |
| Opus 5 | $0.00034 | $0.00477 |
| Sonnet 5 | $0.00013 | $0.00191 |
| Haiku 4.5 | $0.00007 | $0.00096 |
Grade A, and why
council scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Council
Convene a multi-agent council to deliberate on a question. You (Claude) are the chairman. Other CLI agents (Codex, Gemini) provide independent opinions. You synthesize the final verdict.
Usage
The user invokes /council "their question" or /council --with-review "their question".
Step 1: Dispatch the council
Run this bash block. Replace {QUESTION} with the user's actual question text.
COUNCIL_BIN=""; for _d in "$HOME/.claude/skills/agent-council" "$HOME/.agents/skills/agent-council" "$HOME/.gemini/skills/agent-council" "$(git rev-parse --show-toplevel 2>/dev/null)"; do [ -x "$_d/bin/council" ] && COUNCIL_BIN="$_d/bin/council" && break; [ -x "$_d/council" ] && COUNCIL_BIN="$_d/council" && break; done; [ -z "$COUNCIL_BIN" ] && COUNCIL_BIN="$(which council 2>/dev/null || echo "bin/council")"
QUESTION_FILE=$(mktemp /tmp/council-q-XXXXXX)
cat <<'COUNCIL_EOF' > "$QUESTION_FILE"
{QUESTION}
COUNCIL_EOF
SLUG=$(basename "$(git rev-parse --show-toplevel 2>/dev/null || pwd)")
SESSION_DIR=$($COUNCIL_BIN --question-file "$QUESTION_FILE" --project "$SLUG")
rm -f "$QUESTION_FILE"
echo "SESSION_DIR=$SESSION_DIR"
If the user passed --with-review, add that flag to the council command.
If the user passed --quick, add that flag instead.
Step 2: Read the council opinions
After the bash block completes, read the opinion files from the session directory:
- Read
$SESSION_DIR/meta.jsonto understand the session structure - Read each file in
$SESSION_DIR/stage1/(opinion_codex.json, opinion_gemini.json, etc.) - If
--with-reviewwas used, also read files in$SESSION_DIR/stage2/
Step 3: Synthesize as chairman
You are the chairman. You have the full conversation context with the user PLUS the council opinions. Produce the synthesis:
- Consensus: Where all agents agree
- Divergence: Where agents disagree. State each position fairly with agent name.
- Recommendation: Your synthesized answer drawing from the strongest elements.
- Confidence:
- If all agree: HIGH — Strong consensus across models.
- If majority agrees: MEDIUM — Majority view with notable dissent.
- If fundamental disagreement: LOW — Agents fundamentally disagree. For each agent, state: Agent name (their confidence): their position. End with: "This is a decision you should make yourself, not delegate to the council."
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 99 lines · 67 tokens per session scan A f267384ed583
council is a skill published in the GitHub repository yogirk/agent-council (89 stars, last pushed 4mo ago), licensed MIT. It adds 67 tokens to every session and 955 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…