abxn4rabxn4r/archon-skills/.agents/skills/council/SKILL.md

council

Skill1 starsChanged 28 days agoApache-2.0View on GitHub

Autonomous Multi-Advisor Consensus Council orchestrating Seneca (Strategy), Dijkstra (Architecture), Saltzer (Security & Release Veto), Aperture (UI/UX), Caples (Copy), and Orwell (Growth) on high-stakes decisions, migrations, and architecture changes. Produces a unified Consensus & Disagreements Matrix.

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

0
Common
Most of the 109 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Do NOT convene for:
line 39
Distinctive:
All Council participants strictly classify statements by evidence level:
line 49
Distinctive:
Run directly via the zero-dependency CLI:
line 116

“Common” is measured: kept by at least 6 in 10 of the 109 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

ARCHON AUTONOMOUS CONSENSUS COUNCIL

1. PURPOSE & MISSION

The Consensus Council convenes when an engineering, product, or strategic decision carries cross-disciplinary consequences or irreversible risk.

Rather than consulting advisors sequentially or accepting unilateral technical choices, the Council orchestrates an independent debate across all six Archon disciplines:

Seneca (Strategic Advisor & Second Brain) — Evaluates reversibility, leverage, cognitive displacement, and pre-mortem failure modes.
Dijkstra (Engineering Architect) — Enforces structural simplicity, dependency fitness, and long-term codebase health.
Saltzer (Principal Security Engineer) — Audits attack surface expansion, trust boundaries, and exercises Release Veto Authority.
Aperture (Design & UX Director) — Protects user ergonomics, cognitive load, and Linear/Stripe craft standards.
Caples (Copy & Messaging Director) — Demands positioning clarity, empirical proof, and elimination of marketing abstractions.
Orwell (Growth & Content Director) — Evaluates open-source developer reputation, community perception, and algorithmic compounding.

2. WHEN TO CONVENE THE COUNCIL

Convene immediately for:

Database migrations, storage engine transitions, or ORM replacements
Introduction of major infrastructure (microservices, message queues, distributed caches, vector DBs)
Public API design changes or external integration protocols
Authentication, authorization, or cryptographic redesigns
Open-source license changes, monetization shifts, or pricing model revisions
High-friction technical debt disputes between speed and craft
Any Type 1 decision (one-way door) that cannot easily be undone

Do NOT convene for:

Routine bug fixes or localized refactors (use Dijkstra)
Pure styling, CSS, or component polish (use Aperture)
Copy editing or single landing page headlines (use Caples)
Single-file dependency updates

3. EPISTEMIC EVIDENCE STANDARDS

All Council participants strictly classify statements by evidence level:

Observed / Fact: Directly visible in current code, committed config, or verified benchmark output on disk.
Inference: Logical deduction derived strictly from observed evidence.
Hypothesis: Plausible interpretation, risk model, or theory requiring empirical validation.
Unknown: Critical context not available; must be named before ruling.

Speculation presented as certainty is rejected immediately. Absence of evidence is not evidence of security or correctness.

4. THE 3-PHASE DELIBERATION PROTOCOL

Phase 1: Reversibility & Stakes Classification

Type 1 (One-Way Door): Irreversible or prohibitively expensive to reverse. Enforce 48-hour cooling off, pre-mortem, and unanimous consensus.
Type 2 (Two-Way Door): Reversible with low friction. Prioritize execution velocity; require only lightweight guardrails.

Phase 2: Independent Discipline Inquests

Each specialist reviews the proposal from their uncompromising domain standards:

Seneca: "Does this create sustainable leverage, or is this refinement-as-avoidance?"
Dijkstra: "Does this pass the Simplicity Test? What happens if we delete code instead of adding it?"
Saltzer: "What trust boundary changes? Is there an exploitable attack chain? Does a Critical finding exist?"
Aperture: "Does this create user cognitive friction or break our 4px craft invariants?"
Caples: "Can we state the verifiable value of this in one sentence without corporate buzzwords?"
Orwell: "Does this enhance or dilute developer credibility and open-source standing?"

Phase 3: Consensus & Disagreements Synthesis

Cross-reference tensions (e.g. Dijkstra simplicity vs Saltzer defense-in-depth).
Construct the Consensus & Disagreements Matrix.
Apply Saltzer Release Veto: If a Critical vulnerability is identified, the proposal is VETOED — DO NOT SHIP regardless of other votes.

5. OUTPUT FORMAT

# ARCHON EXECUTIVE BOARD CONSENSUS COUNCIL
**Proposal**: "[Proposal Summary]"
**Stakes**: Type 1 (One-Way Door) | Type 2 (Two-Way Door)
**Timestamp**: YYYY-MM-DD HH:MM UTC

## 1. Advisor Inquests
- **Seneca**: [Stance & Leverage Assessment]
- **Dijkstra**: [Simplicity & Architectural Invariant Assessment]
- **Saltzer**: [Attack Surface & Veto Status]
- **Aperture**: [UX & Cognitive Load Impact]
- **Caples**: [Clarity & Value Proof]
- **Orwell**: [Reputation & Community Trajectory]

## 2. Consensus & Disagreements Matrix
| Discipline | Core Requirement | Identified Risk | Resolution |
|---|---|---|---|
| Strategy | ... | ... | ... |
| Architecture | ... | ... | ... |
| Security | ... | ... | ... |
| Design | ... | ... | ... |
| Messaging | ... | ... | ... |
| Growth | ... | ... | ... |

## 3. Final Ruling & Prescribed Invariants
- **Board Verdict**: APPROVED / CONDITIONAL / VETOED
- **Non-Negotiable Invariants**: [1-3 binding rules for implementation]
- **Institutional Record**: Logged to `.archon/council/decisions.jsonl`

6. CLI INVOCATION

Run directly via the zero-dependency CLI:

python -m archon.cli council "Migrate storage from SQLite to PostgreSQL"

Download now (ZIP)

Other versions122 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 122
simstudioai/sim★ 30ksame name
0xNyk/council-of-high-intelligence★ 4.7ksame name
t3dotgg/tstack★ 2.5ksame name
warpdotdev/common-skills★ 630same name
QuixiAI/agi-memory★ 617same name
QuixiAI/Hexis★ 617same name
ZaxbyHub/opencode-swarm★ 517same name
zaxbysauce/opencode-swarm★ 503same name
boshu2/agentops★ 452same name
automagik-dev/genie★ 345same name
112 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Used alongsideProjects with it also use motion-advanced, orch-pipeline and 10 more.
Other files people use alongside this one.
- renepfSkill
  motion-advanced
  Advanced motion patterns for React / Next.js — drag & drop, gestures, text animations, SVG path drawing, custom hooks, imperative sequences (useAnimate), loaders, and the full API decision tree. Requires motion-foundations.
  Also in 4 projects that use this
- renepfSkill
  orch-pipeline
  Shared orchestration engine for the orch-* skill family. Defines the gated Research-Plan-TDD-Review-Commit pipeline, the size classifier, the agent map, and the two human gates that the orch-* operation skills delegate to. Not usually invoked directly.
  Also in 3 projects that use this
- ronmkrSkill
  defi-amm-security
  Security checklist for Solidity AMM contracts, liquidity pools, and swap flows. Covers reentrancy, CEI ordering, donation or inflation attacks, oracle manipulation, slippage, admin controls, and integer math.
  Also in 5 projects that use this
- ronmkrSkill
  vite-patterns
  Vite build tool patterns including config, plugins, HMR, env variables, proxy setup, SSR, library mode, dependency pre-bundling, and build optimization. Activate when working with vite.config.ts, Vite plugins, or Vite-based projects.
  Also in 5 projects that use this
- TironFoxSkill
  agent-payment-x402
  Add x402 payment execution to AI agents — per-task budgets, spending controls, and non-custodial wallets via MCP tools. Use when agents need to pay for APIs, services, or other agents.
  Also in 4 projects that use this
- romaintoso78Skill
  security-bounty-hunter
  Hunt for exploitable, bounty-worthy security issues in repositories. Focuses on remotely reachable vulnerabilities that qualify for real reports instead of noisy local-only findings.
  Also in 7 projects that use this
- +2 more from renepf
- +2 more from ronmkr
In this repository32 other files it gives its agents.
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/aperture.mdcCursor rule
- .cursor/rules/berners.mdcCursor rule
- .cursor/rules/caples.mdcCursor rule
- .cursor/rules/council.mdcCursor rule
- .cursor/rules/dijkstra.mdcCursor rule
- .cursor/rules/orwell.mdcCursor rule
- .cursor/rules/saltzer.mdcCursor rule
- .cursor/rules/seneca.mdcCursor rule
- apertureSkill
- bernersSkill
- caplesSkill
- dijkstraSkill
- orwellSkill
- saltzerSkill
- senecaSkill
- apertureSkill
- bernersSkill
- caplesSkill
- councilSkill
- dijkstraSkill
- orwellSkill
- saltzerSkill
- senecaSkill
- apertureSkill
- bernersSkill
- caplesSkill
- councilSkill
- dijkstraSkill
- orwellSkill
- saltzerSkill
- senecaSkill

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

ARCHON AUTONOMOUS CONSENSUS COUNCIL

1. PURPOSE & MISSION

2. WHEN TO CONVENE THE COUNCIL

3. EPISTEMIC EVIDENCE STANDARDS

4. THE 3-PHASE DELIBERATION PROTOCOL

Phase 1: Reversibility & Stakes Classification

Phase 2: Independent Discipline Inquests

Phase 3: Consensus & Disagreements Synthesis

5. OUTPUT FORMAT

6. CLI INVOCATION

Word for word · 0

Edited · 0

Wrote their own version · 122

motion-advanced

orch-pipeline

defi-amm-security

vite-patterns

agent-payment-x402

security-bounty-hunter

Does it work?

Your trail

Now do this for your own.