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 magnus919/agent-skills --skill agent-councilgit clone --depth 1 https://github.com/magnus919/agent-skillsWrote 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/magnus919/agent-skills/agent-council)<a href="https://agentmods.dev/skills/magnus919/agent-skills/agent-council"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/agent-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/magnus919/agent-skills/agent-council"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/agent-council.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 202 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00129 | $0.04237 |
| Opus 5.5 | $0.00052 | $0.01695 |
| Sonnet 5.5 | $0.00026 | $0.00847 |
| Haiku 4.5 | $0.00013 | $0.00424 |
Grade A, and why
agent-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 1mo 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 — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Council
Spawn a panel of expert agents to debate any question. The council runs a structured protocol — compose, premortem, position, cross-examination (iterative), synthesis — and produces a decision landscape with convergence diagnostics.
When to Use
Invoke the council when any of these apply:
- The question has genuine tradeoffs with no clear correct answer
- You want multi-perspective analysis to surface hidden assumptions
- A decision would benefit from adversarial collaboration
- You want confidence diagnostics (not just a recommendation)
- The question has high stakes or irreversible consequences
Signal phrases: "Let's get multiple perspectives on this" / "Debate this: X" / "What would experts say about X" / "What are we missing?"
Quick Start
1. Install
# One-time setup
pip install pydantic-ai
pip install agent-council
# Or install from this skill directory:
python3 scripts/bootstrap.py
2. Configure
export AGENT_COUNCIL_API_KEY="sk-..."
export AGENT_COUNCIL_MODEL="openai:gpt-5.6-luna"
3. Run
agent-council "Should we use Postgres or SQLite for this service?"
Command Reference
agent-council [OPTIONS] <question>
Options:
--agents, -n {3,4,5,6,7} Number of agents (default: 5)
--mode, -m {quick,medium,deep} Debate depth (default: medium)
--profiles TEXT Comma-separated profile names from the hermes-profiles
library (e.g. "debugger,researcher,product-manager")
--persona-file PATH JSON file with custom agent personas
--json Output structured JSON instead of markdown
--verbose, -v Show phase-by-phase progress
--max-rounds INTEGER Max cross-examination rounds (default: 4)
--convergence FLOAT Convergence threshold (default: 0.10)
Mode Selection
| Mode | Agents | Rounds | When to use |
|---|---|---|---|
quick |
3 | 1 cross-examine round | Low-stakes check, fast answer needed |
medium (default) |
5 | Eval-driven, up to 4 rounds | Standard decisions |
deep |
7 | Eval-driven, up to 4 rounds | High-stakes, hidden assumptions |
What ships with it
25 files 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.
- agent_council/__init__.py 85 B runs code
- agent_council/__main__.py 132 B runs code
- agent_council/cli.py 7.4 KB runs code
- agent_council/config.py 3.2 KB runs code
- agent_council/convergence.py 3.7 KB runs code
- agent_council/graph.py 7.6 KB runs code
- agent_council/guardrails.py 5.1 KB runs code
- agent_council/phases/__init__.py 18 B runs code
- agent_council/phases/compose.py 2.0 KB runs code
- agent_council/phases/cross_examine.py 4.0 KB runs code
- agent_council/phases/position.py 2.8 KB runs code
- agent_council/phases/premortem.py 2.3 KB runs code
- agent_council/phases/select.py 3.4 KB runs code
- agent_council/phases/synthesis.py 8.8 KB runs code
- agent_council/state.py 6.2 KB runs code
- evals/evals.json 6.5 KB
- LICENSE 1.0 KB
- pyproject.toml 560 B
- README.md 3.7 KB
- references/configuration.md 1.8 KB
- references/convergence.md 1.9 KB
- references/debate-protocol.md 2.7 KB
- scripts/bootstrap.py 2.1 KB runs code
- templates/personas.json 1.9 KB
- tests/test_select.py 1.0 KB runs code
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.
- 1mo ago First seen · 345 lines · 129 tokens per session scan A eb4ec52a1998
agent-council is a skill published in the GitHub repository magnus919/agent-skills (151 stars, last pushed yesterday), licensed MIT. It adds 129 tokens to every session and 4,237 once invoked, about $0.0005 per session on Opus 5.5. 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
cocoreview
CocoReview — structured code review with six-severity findings vocabulary, progressive disclosure architecture, and universal anti-pattern baseline. Invoked via $review [file] [--complexity] [--security] [--architecture] [--language ].
cocoharvest
Decompose an approved plan into parallel workstreams, assign specialist personas, classify stages as HITL or AFK (CocoLens), generate flow.json stages with checkpoints and dual-file state, and create per-stage prompt files. Includes adaptive parallelism, stall detection, shell identity injection, and consecutive…
spec
Enter the Spec phase of CocoBrew. Guides the developer through structured requirements capture: goal, success criteria, constraints, personas involved, data sources, and deliverables. Writes spec.md to .cocoplus/lifecycle/ and creates a git commit.
discuss
Run a structured decision-capture dialogue before $plan — locks implementation choices (model, evaluation methodology, accuracy threshold, scope boundaries) into discuss.md to prevent silent decision drift during planning. Supports --red-team flag for adversarial post-PASS challenge session.
cocotrace
Build and query the SHA-256 requirements-to-implementation traceability graph across lifecycle artifacts.
cocoscout
Relevance-ranked context loading — Tier 2 async subagent (Haiku, <5s) that fires after Tier 1 deterministic checks in UserPromptSubmit. Injects ranked context from CocoGrove, CocoContext, Environment Inspector, Prompt Studio, and CocoDream.