IdeaSAFE
The Agent Harness for AI-Human Collaboration, inspired by the AI-DLC (AI-Driven Development Lifecycle)
Overview
The Agent Harness for AI-Human Collaboration, inspired by the AI-DLC (AI-Driven Development Lifecycle)
3bb5b08404b5OBSERVED · 2026-10-12Host compatibility
What the documentation claims. We have not run a compatibility test.
| Host | Status | Notes |
|---|---|---|
| openclaw | mentioned |
What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
---
name: idea
description: Chorus Idea workflow — claim ideas, run elaboration rounds, and prepare for proposal creation.
license: AGPL-3.0
metadata:
author: chorus
version: "0.22.1"
category: project-management
mcp_server: chorus
---
# Idea Skill
This skill covers the **Ideation** stage of the AI-DLC workflow: claiming Ideas, running structured elaboration rounds to clarify requirements, and preparing for Proposal creation.
> **Tool namespace:** Chorus tools are exposed by the connected MCP server under a `chorus__` prefix on OpenClaw (e.g. `chorus__chorus_get_idea`). Bare names are used below for readability — prepend `chorus__` when invoking. See `/chorus` for the full rule.
---
## Overview
Ideas are the starting point of the AI-DLC pipeline. Humans (or Admin agents) create Ideas describing what they need. The PM Agent claims an Idea, runs elaboration to clarify requirements, and then moves on to `/proposal` to create a Proposal with document and task drafts.
**Idea status lifecycle (3 stored states):**
```
open --> elaborating --> elaborated
```
All post-elaboration progress (planning, building, verifying, done) is **derived** from the state of linked Proposals and Tasks. No agent should set Idea status directly beyond elaboration -- all transitions are side-effects of claiming, releasing, or completing elaboration.
---
## Tools
**Idea Management:**
| Tool | Purpose |
|------|---------|
| `chorus_pm_create_idea` | Create a new idea in a project (on behalf of humans). Optional `parentUuid` derives a child idea from an existing same-project idea (single-parent lineage). |
| `chorus_edit_idea` | Edit an existing idea's title, description, and/or lineage parent. `parentUuid`: another same-project idea to reparent under, `null` to detach to top-level, omit to leave unchanged (cycle-checked + same-project). Single-parent **weak** lineage — a parent shows a read-only `+N derived` rollup but never blocks either idea's flow. Records an "edited" activity and signals presence. |
| `chorus_claim_idea` | Claim an open idea (open -> elaborating) |
| `chorus_release_idea` | Release a claimed idea (elaborating -> open) |
| `chorus_pm_assign_idea` | Assign an idea to an agent (must hold `idea:write`) or a user, on a human's behalf — the counterpart to `chorus_claim_idea` (self-claim). Silently takes over any existing assignee; an `open` idea moves to `elaborating`, any other status is preserved. Optional `instanceUuid` pins an **agent** assignment to a specific AgentInstance (agent-only) — but a project-fixed cwd target configured for the owner takes precedence and supplies the instance automatically, overriding `instanceUuid`. Assigning a **new** owner wakes it best-effort (offline still persists the assignment); re-assigning the same owner may update its pin/cwd but is wake-deduplicated. Assigning to a user notifies them with no daemon wake. Requires `idea:admin`. |
| `chorus_move_idea` | Move an Idea to a different Project. Cascade-migrates the Idea **and its full lineage subtree** (all descendant Ideas; the moved root is detached from any parent left behind), all linked Proposals (any status), all materialized Documents and Tasks, and all related Activities atomically. Comments, TaskDependency, AcceptanceCriterion, AgentSession, SessionTaskCheckin, Notification history, and Task assignees are NOT modified. Returns `moved: { ideas, proposals, documents, tasks, activities }` counts. Requires `idea:write` only — no project-level checks. |
**Requirements Elaboration:**
| Tool | Purpose |
|------|---------|
| `chorus_pm_start_elaboration` | Generate an elaboration round (first, follow-up, or appended-after-resolution) |
| `chorus_pm_validate_elaboration` | Mark the whole elaboration complete (requires `idea:admin`; requires human confirmation first) |
| `chorus_pm_skip_elaboration` | Skip elaboration for trivially clear Ideas |
| `chorus_answer_elaboration` | Submit answers for an elaboration round (`roundUuid` optional — auto-locates the active round) |
| `chorus_get_elaboration` | Get full elaboration state (rounds, questions, answers) |
**Shared tools** (checkin, query, comment, search, notifications): see `/chorus`
---
## Tracker Research action: research-only entry
When the current instruction is an explicit Tracker Research action, route directly to `/research` ([research-only contract](../research/SKILL.md)) and the result-saving rules in Step 4.45. Check current authoritative development eligibility before executing. This branch bypasses the normal claim and elaboration sequence below: preserve the existing Idea, root session, pending questions, answers, resolution, proposal approval and task states. Save findings to the latest Idea body with real citations and report, then **return**. If development has begun, report the changed stage without researching or editing. Record impacts on approved scope as follow-up in the Idea; do not mutate locked proposals.
---
## Workflow
### Step 1: Check In
```
chorus_checkin()
```
Review your persona, current assignments, and pending work counts.
### Step 2: Find Work
```
chorus_get_available_ideas({ projectUuid: "<project-uuid>" })
```
Or check existing assignments:
```
chorus_get_my_assignments()
```
### Step 3: Claim an Idea
Claiming automatically transitions the Idea to `elaborating` status:
```
chorus_claim_idea({ ideaUuid: "<idea-uuid>" })
```
### Step 4: Gather Context
Before elaborating, understand the full picture:
1. **Read the idea in detail:**
```
chorus_get_idea({ ideaUuid: "<idea-uuid>" })
```
2. **Read existing project documents** (for context, tech stack, conventions):
```
chorus_get_documents({ projectUuid: "<project-uuid>" })
chorus_get_document({ documentUuid: "<doc-uuid>" })
```
3. **Review past proposals** (to understand patterns and standards):
```
chorus_get_proposals({ projectUuid: "<project-uuid>", status: "approved" })
```
4. **Check existing tasks** (to avTrust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (1)
.agents/skills
Gates applied: no_behavioural_pass.
3bb5b08404b5full audit observations/trust-audit/skill/chorus-aidlc__idea.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-12 | 3bb5b08404b5 | SAFE | B | 89 | first audit |
Questions
What does the Idea skill do?
The Agent Harness for AI-Human Collaboration, inspired by the AI-DLC (AI-Driven Development Lifecycle)
Is Idea safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Idea access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does Idea work with?
Its documentation mentions openclaw. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (3bb5b08404b5), read on 2026-10-12. The repository is watched, and a new audit runs when it changes — this is the first audit.