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/justinjdev/fellowship/councilnpx skills add justinjdev/fellowship --skill councilgit clone --depth 1 https://github.com/justinjdev/fellowshipWrote 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/justinjdev/fellowship/council)<a href="https://agentmods.dev/skills/justinjdev/fellowship/council"><img src="https://agentmods.dev/badge/skills/justinjdev/fellowship/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 | $0.00055 | $0.01170 |
| Opus 5 | $0.00028 | $0.00585 |
| Sonnet 5 | $0.00011 | $0.00234 |
| Haiku 4.5 | $0.00006 | $0.00117 |
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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Council — Context-Aware Task Onboarding
Overview
Loads focused, task-relevant context at the start of any non-trivial work session. Produces a structured Session Context block that serves as the foundation for all downstream work. This is the "onboarding the agent within every repo" pattern from context engineering.
When to Use
- Starting any task that involves more than a quick fix
- Beginning a new session on existing in-progress work
- Invoked automatically as Phase 0 of
/quest
Process
Step 0: Check for Existing Checkpoint
Before doing anything else, check if .fellowship/checkpoint.md exists (in repo root). (.fellowship/ is the default data directory; users can override it via dataDir in ~/.claude/fellowship.json.)
If it does:
- Read the checkpoint file
- Present the checkpoint summary to the user
- Ask: "Found a checkpoint from [timestamp] on branch [branch]. Resume from where you left off, or start fresh?"
- If resuming: load the checkpoint as the Session Context. Skip Steps 1-4 and go directly to Step 5 (confirm with user).
- If starting fresh: delete the checkpoint file and continue with Step 1.
Step 1: Read Project Context
Read the root CLAUDE.md. Extract:
- Reference files relevant to the task area
- Review conventions that apply
- Architecture constraints
If no CLAUDE.md exists, note: "Consider running /chronicle to set up project context."
Also check for ~/.claude/fellowship.json (the user's personal Claude directory). If it exists, read it and note any non-default settings. These will be included in the Session Context block under Architecture Notes so downstream skills (quest, lembas) are aware of the active configuration.
Step 2: Understand the Task
Ask one focused question:
"What are you working on? (One sentence describing the task and which area of the codebase it touches.)"
If invoked by quest, the task description is passed in — skip the question.
Step 3: Identify Package Scope
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 · 116 lines · 55 tokens per session scan A 080077ef2a2c
council is a skill published in the GitHub repository justinjdev/fellowship (5 stars, last pushed 21d ago), licensed Apache-2.0. It adds 55 tokens to every session and 1,170 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 2026-08-31.
Other skills, from other repositories
continuous-learning
ProductionOS instinct-based learning system. Observes sessions via hooks, extracts patterns, creates atomic instincts with confidence scoring, and auto-promotes high-confidence patterns across projects.
productionos
ProductionOS — dual-target AI engineering operating system for repo-wide audits, upgrade plans, code reviews, strategic product reviews, security sweeps, UX audits, and recursive quality improvement.
frontend-audit
ProductionOS frontend quality scanner. Auto-activates when editing React/Vue/Svelte components, CSS, or layout files. Checks accessibility, responsive design, performance, and design system consistency.
security-scan
ProductionOS security scanner. Auto-activates when editing auth, payment, credential, or admin files. Runs OWASP Top 10 checks, dependency audit, and secret detection.
roadmap
Ongoing entry point for a project's ROADMAP.jsonl. Pick the next task to work on (ranks candidates deterministically by dependencies and file-touch collisions, shows why each is where it is, then crafts a self-contained handoff prompt), add a new task, correct a stale one, review roadmap status, or check the roadmap's…
ai-instruction-detox
AI 指令排毒與規則治理：把散落在 CLAUDE.md、AGENTS.md、skills、context、memory 的規則 原子化、查衝突、去重複、找過時、揪 Prompt Injection，產出可套用的精簡架構與回復方案。 觸發時機：用戶說「指令排毒」「規則太亂」「CLAUDE.md 太長」「規則互相矛盾」「上下文減肥」 「AI 設定治理」「多個 Agent 規則分裂」「context 膨脹」，或要求審查／清理 AI 指令檔。 不要觸發：一般程式重構、產品程式碼審查、單純想縮短一份文件（那是編輯不是治理）。.