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 skills add blakecyze/kanso --skill kanso-councilgit clone --depth 1 https://github.com/blakecyze/kansoWrote 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/blakecyze/kanso/kanso-council)<a href="https://agentmods.dev/skills/blakecyze/kanso/kanso-council"><img src="https://agentmods.dev/badge/skills/blakecyze/kanso/kanso-council/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/skills/blakecyze/kanso/kanso-council"><img src="https://agentmods.dev/badge/skills/blakecyze/kanso/kanso-council.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 | $0.00090 | $0.01965 |
| Opus 5 | $0.00045 | $0.00983 |
| Sonnet 5 | $0.00018 | $0.00393 |
| Haiku 4.5 | $0.00009 | $0.00197 |
Grade A, and why
kanso-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 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kanso-council
A stronger audit. Every capable agent CLI on the machine reviews the same scope under kanso-audit's framework, independently and in parallel, and the reports merge into one consensus-weighted findings list. Agreement between independent models is strong signal; a finding three engines converge on is rarely noise.
The council changes who reviews, never what happens next. Findings land in kanso-audit's report format, end at kanso-audit's approval gate, and route through its Phases B, C, and D unchanged. This skill owns Phase A only.
The roster
Four engines are known. The host CLI (the one this session runs in) always sits on the council and audits inline; the others are detected with command -v and run headless in their own worktrees. An absent engine is skipped with a one-liner, never an error.
Model policy: family aliases and CLI defaults only. A dated model ID in this file is a bug. Aliases and defaults track each vendor's current flagship, so a new model generation needs zero edits here.
| Engine | Headless invocation | Model | Effort |
|---|---|---|---|
| codex | codex exec "<prompt>" |
CLI default (current flagship) | -c model_reasoning_effort="low" |
| cursor-agent | cursor-agent -p --output-format text "<prompt>" |
--model grok (family alias) |
none available |
| claude | claude -p "<prompt>" |
--model opus (family alias) |
CLI default (medium) |
| gemini | gemini -p "<prompt>" |
CLI default | none |
If an alias errors because the vendor renamed it, drop the model flag, rerun on the CLI default, and note the substitution in the roster line. Per-run overrides win over the table: --codex-model=x maps to that engine's model flag verbatim.
Open the report with the roster:
Council: host (claude) + codex + grok · gemini not found, skipped
Resolve the scope
Same grammar as kanso-audit: diff (default), branch, a module path, or all. Resolve it once, before dispatch, and capture the concrete input (the diff text, or the file list for path and all scopes) so every engine reviews identical material. A council where each member reads a different tree is theatre.
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 · 119 lines · 90 tokens per session scan A 9df304723e5e
kanso-council is a skill published in the GitHub repository blakecyze/kanso (3 stars, last pushed 7d ago), licensed MIT. It adds 90 tokens to every session and 1,965 once invoked, about $0.0005 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 2026-09-05.
Other skills, from other repositories
code-reviewer
Code review knowledge base: quality, security (OWASP Top 10), error-handling, performance, and test-coverage checklists with severity-ranked output format. Use when reviewing code changes, PRs, or before commits. Loaded automatically by the code-reviewer agent.
mutation-test
Mutation testing with two engines. Uses the project's NATIVE mutation runner (StrykerJS / Infection / mutmut / PIT / cargo-mutants) when one is configured — installing it on explicit consent when it is not — for a reproducible, comparable score; and an LLM-guided engine for the mutation classes native mutators cannot…
review
Structured code review with parallel audit agents, confidence-scored triage, and optional auto-fix. Examines uncommitted changes, staged diffs, commit ranges, or specific paths. Produces a tiered report (MUST-FIX / RECOMMENDED / NIT) backed by evidence, then optionally applies fixes with verification.
db-audit
Database performance and safety audit. 70+ checks across 13 dimensions (DB1-DB13): query patterns, indexes, schema design, connections, transactions, migrations, caching, query optimization, ORM anti-patterns, observability, data lifecycle, DB security, and migration deployment safety. Code-level checks for all ORMs.…
write-tests
Write tests for existing production code. Processes ONE file at a time through a full pipeline: analyze, inventory (frozen BEFORE writing), write, executable coverage gate, verify, blind coverage audit, adversarial review, log. Uses CodeSift for discovery and analysis when available. Modes: [path] (specific target)…
brainstorm
Explores a codebase, researches the problem space, and produces an approved design specification before any code is written. Use when the user wants to create a new feature, add significant functionality, redesign a subsystem, or build something that touches multiple parts of the project.