elicitation

A self-review step for an expert coding agent after implementation and before final validation.

In plain words
What is it for?
Use it to review completed code manually, automatically, or not at all, and save the review result for comparison with later passes.
Why use it?
It provides a structured pause to find gaps, correct mistakes, or record remaining issues before another check runs.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/fusengine/agents/elicitation
Any agent
npx skills add fusengine/agents --skill elicitation
Clone the repo
git clone --depth 1 https://github.com/fusengine/agents

Made for: Claude Code, Codex.

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,499 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00034 $0.01499
Opus 5 $0.00017 $0.00749
Sonnet 5 $0.00007 $0.00300
Haiku 4.5 $0.00003 $0.00150

Measured yesterday against content hash c815d9059277, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

elicitation 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 yesterday.

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.

plugins/ai-pilot/skills/elicitation/SKILL.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

It sits between Execute and eXamine in the APEX flow, scores itself against an exit threshold (>=90% proceed, 70-89% document gaps, <70% iterate), and persists its findings to .claude/apex/docs/elicit-{task-slug}.json so a later pass can diff against prior verdicts instead of restarting.

Elicitation Skill

Purpose

Enable expert agents to self-review and self-correct their code before external validation (sniper). Based on BMAD-METHOD's 75 elicitation techniques.


3 Execution Modes

Mode 1: MANUAL (default)

Expert presents 5 relevant techniques → User chooses → Expert applies

Mode 2: AUTO (--auto)

Expert auto-detects code type → Auto-selects techniques → Applies silently

Mode 3: SKIP (--skip)

Skip elicitation → Go directly to sniper validation

Quick Start

After Execute phase, expert runs:

# Manual mode (default)
> Apply elicitation skill

# Auto mode (no prompts)
> Apply elicitation skill --auto

# Skip self-review
> Apply elicitation skill --skip

Workflow Overview

┌─────────────────────────────────────────────────────────┐
│              ELICITATION WORKFLOW                       │
│                                                         │
│  Step 0: Init           → Load context                 │
│  Step 1: Analyze Code   → Detect code type             │
│  Step 2: Select         → Choose techniques (or auto)  │
│  Step 3: Apply Review   → Execute techniques           │
│  Step 4: Self-Correct   → Fix own issues               │
│  Step 5: Report         → Summary before sniper        │
└─────────────────────────────────────────────────────────┘

Read the full file on GitHub · 170 lines

Changes

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.

  1. yesterday First seen · 170 lines · 34 tokens per session scan A c815d9059277

Subscribe to this mod's changes

elicitation is a skill published in the GitHub repository fusengine/agents (25 stars, last pushed 28d ago), licensed MIT. It adds 34 tokens to every session and 1,499 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.