APIbase: Command for Claude Code

.claude/commands/councilreview.md

councilreview is a command for Claude Code from whiteknightonhorse/APIbase. It costs 0 tokens per session (3,557 once invoked), scanned A, original, MIT.

A review command that examines a code change through eight independent expert viewpoints. It reports issues with severity, file and line, explanation, and a concrete fix, then applies safe fixes for lower-severity findings.

In plain words
What is it for?
Reviewing a commit, feature branch, or uncommitted change before it is accepted.
Why use it?
It gathers different kinds of review in one pass, helping reveal security, quality, and other problems that one reviewer may miss.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is whiteknightonhorse/APIbase's own configuration. It tells Claude Code how to work on APIbase itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything APIbase configures →

Reuse

Borrowing it

Nothing to install: this file belongs to whiteknightonhorse/APIbase. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/whiteknightonhorse/APIbase/main/.claude/commands/councilreview.md
Clone the repo
git clone --depth 1 https://github.com/whiteknightonhorse/APIbase

Made for: Claude Code.

Wrote 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.

agentmods badge for councilreview

README.md
[![agentmods](https://agentmods.dev/badge/commands/whiteknightonhorse/apibase/councilreview/github.svg)](https://agentmods.dev/commands/whiteknightonhorse/apibase/councilreview)
Your own site
<a href="https://agentmods.dev/commands/whiteknightonhorse/apibase/councilreview"><img src="https://agentmods.dev/badge/commands/whiteknightonhorse/apibase/councilreview/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.

agentmods 80×15 button for councilreview

Your own site · 80×15
<a href="https://agentmods.dev/commands/whiteknightonhorse/apibase/councilreview"><img src="https://agentmods.dev/badge/commands/whiteknightonhorse/apibase/councilreview.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,557 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.03557
Opus 5 $0.00000 $0.01778
Sonnet 5 $0.00000 $0.00711
Haiku 4.5 $0.00000 $0.00356

Measured 11d ago against content hash 6a1af4c0f5ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

councilreview 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.

.claude/commands/councilreview.md · 273 lines

How it starts

The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-Expert Council Review

You are a panel of 8 independent expert reviewers. Each expert analyzes the same diff but from their specialized perspective. Experts do not coordinate -- they review independently and may contradict each other. After all reviews, an Auto-Fix phase applies safe fixes for LOW/MEDIUM findings.

Step 1: Get the diff

Run git diff HEAD~1 to get the changes from the last commit. If on a feature branch, use git diff main...HEAD instead. If reviewing pending uncommitted changes, use git diff HEAD.

Read the full diff. Then read the complete file for every changed file (not just the diff context).

Step 2: Run 8 independent expert reviews

Each finding MUST include:

  • severity: CRITICAL / HIGH / MEDIUM / LOW
  • file:line (so auto-fix can locate it)
  • issue (1-2 sentence description)
  • fix (concrete: what code change resolves it — must be specific enough to execute, not "consider X")

Expert 1: Security Architect

Focus areas:

  • Attack surface changes -- new endpoints, new user inputs, new external data flows
  • Authentication and authorization -- bypasses, missing checks, privilege escalation
  • Cryptographic usage -- weak algorithms, static keys, improper random generation
  • Injection vectors -- SQL, NoSQL, command, SSRF, XSS, path traversal, URL injection
  • Secrets management -- hardcoded credentials, secrets in logs, keys in error responses
  • OWASP Top 10 applicability to this change
  • For this project: x402/MPP payment bypass, escrow integrity, API key handling (SHA-256 hashed), MCP protocol auth, hot wallet key handling

Output 1-3 findings. Verdict: PASS / CONCERN / BLOCK


Expert 2: Performance Engineer

Focus areas:

  • Latency impact -- new synchronous operations in hot paths, blocking I/O
  • Throughput -- N+1 queries, unbounded result sets, missing pagination
  • Memory -- leaks (uncleaned listeners, growing maps), large allocations per request
  • Scaling bottlenecks -- single-threaded locks, global state, connection pool exhaustion
  • Caching -- missing cache for expensive operations, incorrect TTL, cache invalidation bugs
  • Database -- missing indexes, full table scans, unoptimized JOIN patterns
  • For this project: Redis single-flight dedup, per-tool cache TTL, Prisma connection pool limits (API: 20, Worker: 10), provider timeout 10s, max response 1MB, 13-stage pipeline latency budget

Read the full file on GitHub · 273 lines

Changes

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.

  1. 11d ago First seen · 273 lines · 0 tokens per session scan A 6a1af4c0f5ad

Subscribe to this mod's changes

councilreview is a command published in the GitHub repository whiteknightonhorse/APIbase (10 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,557 tokens. 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.