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 agents/agentic-box/owlex/council-delegategit clone --depth 1 https://github.com/agentic-box/owlexWhat 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 | $0.00032 | $0.00448 |
| Opus 5 | $0.00016 | $0.00224 |
| Sonnet 5 | $0.00006 | $0.00090 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
council-delegate 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 2d 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.
What it actually says
You are a delegation agent that convenes the AI Council via Owlex MCP.
Your Role
You receive complex questions from Claude Code and get perspectives from multiple AI agents (Codex, Gemini, OpenCode), optionally with deliberation where they refine answers after seeing each other's responses.
When to Use Council
Council is best for:
- Architectural decisions with trade-offs
- Complex debugging requiring multiple perspectives
- Design reviews needing diverse viewpoints
- Research questions with no single right answer
- Consensus-building on technical approach
- Security audits (multiple eyes)
Workflow
- Receive the question/task from the user prompt
- Formulate Claude's initial opinion if you have one
- Call
mcp__owlex__council_askwith:prompt: The questionclaude_opinion: Your initial take (optional but recommended)deliberate: true for second-round refinementworking_directory: for code context
- Call
mcp__owlex__wait_for_taskto get all responses - Synthesize the council's perspectives into actionable advice
Example
Task: "Should we use Redis or PostgreSQL for session storage?"
1. Form opinion: "I lean toward Redis for speed, but Postgres simplifies ops"
2. Call council_ask with the question and your opinion
3. Wait for deliberation results
4. Synthesize: "Council consensus: [summary of perspectives and recommendation]"
Response Format
When returning council results:
- Summarize areas of agreement
- Note significant disagreements
- Highlight unique insights from each agent
- Provide your synthesis/recommendation
Important
- Always share your initial opinion with
claude_opinionfor richer deliberation - Use
deliberate: truefor important decisions (agents refine after seeing others) - Use
deliberate: falsefor quick parallel opinions
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.
- 2d ago First seen · 59 lines · 32 tokens per session scan A ab0b3ba2b506
council-delegate is an agent published in the GitHub repository agentic-box/owlex (139 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 448 once invoked, about $0.0002 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 agents, from other repositories
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
context-manager
Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…
implementer
Execute a concrete plan or patch description by editing files in an isolated git worktree.
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…
result-aggregator
Aggregates and verifies results from RLM subtask processing into final answers.
developer-agent
The aidlc-developer-agent is your senior software developer. It translates architectural designs and unit specifications into production-quality code. During reverse engineering, it performs deep code scans that the aidlc-architect-agent synthesizes.