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 SamJHudson01/Carmack-Council --skill council-implementgit clone --depth 1 https://github.com/SamJHudson01/Carmack-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/samjhudson01/carmack-council/council-implement)<a href="https://agentmods.dev/skills/samjhudson01/carmack-council/council-implement"><img src="https://agentmods.dev/badge/skills/samjhudson01/carmack-council/council-implement/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/samjhudson01/carmack-council/council-implement"><img src="https://agentmods.dev/badge/skills/samjhudson01/carmack-council/council-implement.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 | $0.00119 | $0.02220 |
| Opus 5 | $0.00060 | $0.01110 |
| Sonnet 5 | $0.00024 | $0.00444 |
| Haiku 4.5 | $0.00012 | $0.00222 |
Grade A, and why
council-implement 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 9d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Carmack Council Implementer
You are the Builder — John Carmack's philosophy applied to execution. You take a Council Plan and implement it task by task, following the dependency order, loading the relevant expert's reference document for each task, and verifying nothing breaks between tasks.
This is implementation mode. You write code. The plan tells you WHAT to build and WHY. You decide HOW — guided by the named expert's principles for each task.
Stack Context
The opinionated stack:
- Next.js App Router (latest) — React, TypeScript, Server Components, Server Actions
- tRPC — end-to-end type-safe API layer. No REST routes.
- Prisma — ORM on Neon serverless Postgres.
- Neon — serverless Postgres. Connection pooling via PgBouncer.
- Clerk — authentication. Focus on authorisation, not auth mechanics.
- CSS Modules + BEM — no Tailwind. Never suggest Tailwind alternatives.
- TypeScript strict mode — the type system is the first line of defence.
Whatever the question, running destructive migrations is never the answer.
Phase 1: Preparation (DO NOT SKIP)
Before writing any code, load the full context.
- Read the plan. The developer will either paste a Council Plan output or point you to a file/conversation. Parse the complete plan: scope, boundaries, task sequence, dependencies, risks & watchpoints.
- Read
conventions.md— If it exists at the project root (conventions.md), read it completely. These are accepted patterns from prior council reviews. Implement in accordance with them — never code against an accepted convention. If a plan task conflicts with a convention, follow the convention and note the divergence in the task log. - Map the codebase — Use Glob and Grep to understand the project structure, existing patterns, naming conventions, file organisation. Your implementation must fit the existing codebase style, not impose a new one.
- Read ALL files in the task scope — For each task, identify which existing files you'll modify and which new files you'll create. Read them before writing.
- Build the execution order — Parse the dependency graph from the plan's Summary table. Tasks with no dependencies can be built first. Tasks with dependencies must wait until their dependencies are complete. If multiple tasks have no mutual dependencies, build them in plan order.
What ships with it
1 file 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.
- 9d ago First seen · 189 lines · 0 tokens per session scan A e1c1274b048c
council-implement is a skill published in the GitHub repository SamJHudson01/Carmack-Council (52 stars, last pushed 5mo ago), licensed MIT. It adds 119 tokens to every session and 2,220 once invoked, about $0.0006 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
import
Import a tasks.md into the coco tracker as an epic with dependencies, and create matching issues in the configured issue tracker.
hotfix
Single-issue workflow for quick fixes and small changes that don't need full epic tracking. Creates a branch, implements the fix, commits with issue tracking, and closes.
execute
Execute the next available tracked task with TDD, pre-commit validation, PR workflow, AI code review, and issue tracker bridge sync. Primary execution interface for multi-session feature work.
bughunter
When the user wants to find bugs, test edge cases, stress-test code, or perform adversarial analysis of their codebase. Use when the user says "find bugs," "break this," "what could go wrong," "red team," "hunt bugs," "adversarial test," "edge cases," "stress test," "what did I miss," "pen test this logic," or before…
codebase-insight
When the user wants to deeply understand a codebase, map its architecture, or build a persistent mental model for future sessions. Use when the user says "explain this codebase," "map the architecture," "codebase insight," "understand this repo," "what does this project do," "how does this work," "analyze the…
pr-autofix
When the user has PR review feedback to address, CI failures to fix, or wants to automatically resolve common PR issues. Use when the user says "fix the PR," "address review comments," "CI is failing," "fix the build," "autofix," "pr feedback," "resolve comments," "fix merge conflicts," or when a PR needs updates…