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 commands/sergei-aronsen/claude-code-toolkit/councilgit clone --depth 1 https://github.com/sergei-aronsen/claude-code-toolkitWrote 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/commands/sergei-aronsen/claude-code-toolkit/council)<a href="https://agentmods.dev/commands/sergei-aronsen/claude-code-toolkit/council"><img src="https://agentmods.dev/badge/commands/sergei-aronsen/claude-code-toolkit/council.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 | $0.00000 | $0.02448 |
| Opus 5 | $0.00000 | $0.01224 |
| Sonnet 5 | $0.00000 | $0.00490 |
| Haiku 4.5 | $0.00000 | $0.00245 |
Grade A, and why
council scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
bash <(curl -sSL https://raw.githubusercontent.com/sergei-aronsen/claude-code-toolkit/main/scripts/setup-council.sh) How it starts
The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/council — Multi-AI Plan Validation (Supreme Council)
Purpose
Challenge an implementation plan with Gemini (The Skeptic) and ChatGPT (The Pragmatist) before coding. The Council is not a linter — it validates whether the approach is justified, well-scoped, and free of common production-readiness traps.
Usage
/council <feature description>
Examples:
/council add OAuth login with Google/council refactor payment service to Stripe SDK v3/council implement role-based permissions
Modes
brain.py (the orchestrator behind this command) supports three modes
plus an audit-review mode. Pick the one that matches your task.
validate-plan (default)
/council <feature description>
brain "<feature description>"
Runs Skeptic + Pragmatist over the plan plus the auto-collected
project context (CLAUDE.md, README, planning docs, recent commits,
TODOs, git diff, matching test files, all secret-redacted). Produces
a final consolidated verdict (PROCEED / SIMPLIFY / RETHINK / SKIP)
plus a TL;DR block at the top of the report.
Output: .claude/scratchpad/council-report.md
audit-review
/council audit-review --report <path-to-audit-report>
brain --mode audit-review --report <path>
Per-finding verdict table with header
| ID | verdict | confidence | justification | (REAL / FALSE_POSITIVE / NEEDS_MORE_CONTEXT) plus an in-place rewrite of the report's
## Council verdict slot and the YAML council_pass: frontmatter key.
Mandatory in /audit Phase 5. Prompt template:
scripts/council/prompts/audit-review.md.
retro
brain --mode retro --commit <sha>
Reads the commit's diff plus the Council report saved before the
commit, then asks the Pragmatist whether the implementation matches
what was approved. Output: ALIGNED / DRIFT / UNCLEAR.
Flags
| Flag | What it does | Phase |
|---|---|---|
--no-cache |
Bypass the content-hash cache and force a fresh run | SP6 |
--dry-run |
Build full prompts + show estimated cost; no API calls | SP8 |
--format json |
Emit single-line JSON instead of markdown report | SP8 |
--lang en|ru|auto |
Council prompt language (default auto = detect from CLAUDE.md) |
SP9 |
--commit <sha> |
Required with --mode retro |
SP8 |
--report <path> |
Required with --mode audit-review |
SP1 |
--with-facts |
Slash-command pre-flight: extract factual claims, fact-check via comet-bridge MCP, pass annotated plan to brain.py |
v6.7 |
--strict-facts |
With --with-facts: fail loudly if comet-bridge is unavailable instead of silently skipping the pre-flight |
v6.7 |
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 · 278 lines · 0 tokens per session scan A fe2fe81f3260
council is a command published in the GitHub repository sergei-aronsen/claude-code-toolkit (5 stars, last pushed 18d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,448 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
review-renovate
Review and merge renovate PRs with automerge configuration updates.
monitor-ci
Monitors pull request CI checks until they are resolved (pass or fail).
plan-regression-tests
Plan regression tests for existing code with it.skip statements.
config
Command "config" from sdebruyn/fabric-dw-mcp-cli, covering configuration & defaults, http retry budget, sql retry budget, mcp workspace allowlist {#mcp-workspace-allowlist} and mcp server log level.
database-setup
Use when a project needs to store data and has no database yet. Setting up Supabase, creating tables, writing queries, and connecting them to the frontend. Written for designers.
ingest
Manually add knowledge to the Weaviate store.