# Moa Candidate

> Use when Pafi asks for “MoA candidate mode”, “MoA/council QA”, “compare default vs council vs MoA”, “is this worth MoA?”, or when a request affects Hermes routing, profile/SOUL/skill policy, architecture, sensitive final QA, RUO/Supabase safety, OpenClaw retirement, or high-stakes strategy. This skill classifies whether MoA-style synthesis or a council critique pattern is worth the cost and returns a decision packet. It does not enable live MoA routing by itself.

- Skill: `cryptopafi/moa-candidate` (Agent Skill, multi-file: 7 files)
- Install (CLI): `npx skillmds@latest add cryptopafi/moa-candidate`
- Raw SKILL.md: https://api.skillmd.com/api/skills/cryptopafi/moa-candidate/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: cryptopafi (https://skillmd.com/u/cryptopafi)
- Updated: 2026-09-21
- Page: https://skillmd.com/skills/cryptopafi/moa-candidate

---


# MoA Candidate Mode

## Purpose

Use this skill to decide whether a task deserves multi-model synthesis/review treatment instead of a fast single-model answer.

This is an **operating protocol**, not a live feature switch. It does **not** change Hermes routing, model defaults, approval gates, or paid-tool use. It gives Hermes a consistent classification and output shape until a dedicated MoA runtime route is actually wired and evaluated.

## Source artifacts

Read these if the task is non-trivial or if you need exact policy wording:

- `references/PROC-HERMES-MOA-EVAL.md` — formal procedure and enforcement loop
- `references/moa-operating-policy.md`
- `references/moa-candidates-manifest.md`
- `references/openclaw-retirement-moa-positioning.md`

The skill is self-contained: all required source artifacts above are bundled under `references/`. Historical import provenance can live elsewhere, but runtime use must not depend on absolute local paths outside this skill directory.

Optional integrations: Cortex, LLM-Wiki, and a council implementation such as `/llm-council` may improve evidence capture or critique quality when available, but they are not required for basic skill execution. If those integrations are unavailable, return the decision packet inline and use the local `evals/runs/` record path when an eval run is performed.

## Core distinction

| Layer | Job | Use when |
|---|---|---|
| Default single model | Fast answer / normal execution | low-risk, simple, deterministic, time-sensitive |
| council critique pattern | adversarial lenses + peer review + chairman verdict; `/llm-council` is one implementation when available | disagreement, blind spots, policy conflict, high-stakes decision |
| MoA candidate | same prompt through multiple models + aggregator-style synthesis | answer quality/synthesis matters more than speed/cost |
| Hermes profiles | task ownership + tools + safety envelope + evidence | work requires execution, specialist tools, boundaries, recurring responsibility |

## Automatic classification

Classify as `MOA_CANDIDATE: yes` when the task involves any of:

- Hermes routing/model-policy changes
- profile, SOUL, skill, or prompt changes
- architecture decisions
- sensitive final QA before Pafi uses/sends a report
- strategy decisions where a wrong answer is costly
- coding patch review where a missed regression matters
- conflicting source synthesis
- RUO/Supabase safety/guardrail decisions
- OpenClaw retirement or Hermes operations-layer positioning

Classify as `MOA_CANDIDATE: no` for:

- casual chat
- simple summaries
- single-source lookups
- routine file reads
- deterministic system checks
- low-risk command execution
- tasks where specialist profile routing is the real issue, not answer synthesis

## Operating flow

When triggered explicitly or classified as candidate:

1. **State classification**
   - `MOA_CANDIDATE: yes/no`
   - `Best route: default | council critique pattern | MoA-style synthesis | specialist profile | hybrid`
   - one-line reason

2. **Respect specialist routing first**
   - If the task clearly belongs to an active specialist profile, route/delegate according to Hermes profile policy.
   - MoA does not bypass profile activation, egress guards, approval triggers, or draft-only limits.

3. **Choose the review shape**
   - Use a council critique pattern when disagreement, risk, or blind-spot discovery matters. Use a local council implementation only if callable; otherwise perform the critique pattern inline.
   - Use MoA-style synthesis shape when the task needs the best synthesized answer from multiple plausible views.
   - Use hybrid when both are needed: council critiques first, synthesis after.

4. **Produce a decision packet**
   Include:
   - objective
   - evidence used / evidence still missing
   - default answer
   - critique or alternative lenses
   - synthesized recommendation
   - risks / caveats
   - verification step, including tool-access isolation when MoA-style synthesis is used
   - final verdict: act now / test first / ask Pafi / reject / route to specialist

5. **Eval logging when useful**
   If the task matches `references/moa-candidates-manifest.md`, mention the eval ID.
   If you actually compare a candidate task across `default`, `council critique pattern`, `MoA-style synthesis`, `specialist profile`, or `hybrid` routes, write a run record under `evals/runs/YYYY-MM-DD-<task-id>.md` using the manifest fields: task ID, prompt/input artifact, route used, model(s), latency, estimated cost if available, output artifact, tool-access isolation evidence, judge notes, failure modes, and recommendation. If `evals/runs/` is unavailable or persistence fails, return the full eval record inline and state the skipped-write reason in the decision packet. If you do not write a run record, state why in the decision packet.

## Output template

```markdown
MOA_CANDIDATE: yes|no
Best route: default | council critique pattern | MoA-style synthesis | specialist profile | hybrid
Reason: <one line>

## Decision packet

| Section | Finding |
|---|---|
| Objective | ... |
| Evidence used | ... |
| Missing evidence | ... |
| Default answer | ... |
| Critique / alternate lenses | ... |
| Synthesis | ... |
| Risks | ... |
| Verification | include no live routing change; include reference-model no-tools / aggregator-only tool access check when MoA-style synthesis is used |
| Verdict | act now / test first / ask Pafi / reject / route |

## Next action
<one concrete next action>

VK: [MOA-CANDIDATE] classification={yes|no} route={default|council critique pattern|MoA-style synthesis|specialist profile|hybrid} verdict={act now|test first|ask Pafi|reject|route}
```

For short chat answers, compress the table but preserve classification, route, reason, verdict, and next action.
Always preserve the VK line, even in compressed answers, so downstream audits can verify that classification and route selection occurred.

## Benchmark guardrail

Public benchmark claims about MoA are contextual market intel and non-evidence for Hermes routing until reproduced locally. Do not change Hermes default routing, model ranking, approval policy, or live execution behavior based only on claimed percentages.

Promotion requires local evals comparing:

1. single `gpt-5.6-sol`
2. council critique pattern where relevant (`/llm-council` only when available)
3. MoA route if/when available

Promotion threshold: MoA must beat baseline on at least three real Hermes tasks and preserve safety-boundary compliance.

## Hard limits

- Do not use MoA as a reason to bypass explicit approval.
- Do not use MoA as a reason to bypass active-only specialist profile checks.
- Do not turn public benchmark claims into policy or evaluation evidence unless locally reproduced.
- Do not silently use paid/metred routes unless the active profile/policy allows it.
- Do not overuse this for routine tasks.
- Do not give reference/advisor model outputs tool access in MoA-style synthesis; only the final acting aggregator may use tools, and only when the active runtime policy permits those tools.

## Update protocol

- Bump the patch version for wording-only clarifications.
- Bump the minor version when trigger behavior, output contract, eval logging, or safety boundaries change.
- Keep required runtime references inside this skill directory; use relative paths from `SKILL.md`.
- Re-run Audit Pro after changing the operating flow, output template, hard limits, or bundled references.

## Examples

### Example 1 — routing change

User: `Use MoA candidate mode on this: should Hermes route all code tasks to hermes-coding?`

Response shape:

- `MOA_CANDIDATE: yes`
- `Best route: council critique pattern`
- Reason: profile routing and safety policy affected
- Deliver a decision packet with evidence, risks, fallback, and test plan.

### Example 2 — simple lookup

User: `Is port 443 open?`

Response shape:

- `MOA_CANDIDATE: no`
- `Best route: default`
- Reason: deterministic system check
- Run the check directly.

### Example 3 — final QA

User: `MoA/council QA this before I use it: <report>`

Response shape:

- `MOA_CANDIDATE: yes`
- `Best route: hybrid`
- Reason: final-use report benefits from critique plus synthesis
- Check factual risk, missing evidence, policy violations, overclaiming, and final framing.

## Changelog

| Version | Date | Changes |
|---|---|---|
| 1.2.1 | 2026-06-28 | Added eval-run template and tightened council portability wording after PASS quick wins. |
| 1.2.0 | 2026-06-28 | Normalized route enum across decision packets and eval records; added scored judge rubric and packaged eval-run README. |
| 1.1.0 | 2026-06-28 | Added optional integration fallback wording, eval write fallback, portable council route naming, non-evidence benchmark wording, and elevated MoA tool-access isolation into the primary verification contract and hard limits. |
| 1.0.1 | 2026-06-28 | Bundled required references locally; switched runtime links to relative paths; added durable eval-run rule, VK output contract, and update protocol after Audit Pro findings. |
| 1.0.0 | 2026-06-27 | Initial local MoA candidate operating protocol imported from Hermes. |