Target organization: <ORG> (exists, 0 agent(s) besides root; apply_org adds to it)

Show the block below to the user exactly as written, from its first line up to (not including) the marker line; one plain-words intro line before it is fine.

PLAN FOR YOU
Goal: Produce a sourced competitor analysis of five self-hosted note-taking apps for a small team choosing one.
What I understood you need:
- Scope: Obsidian, Logseq, Joplin, Trilium and AnyType only; self-hosting, licensing, sync/E2EE, mobile support, extensibility.
- Quality bar: Every factual claim cites the page that states it; opinions are labelled as judgement, without citations; current facts (versions, licenses) come from the live source.
- Sources: Web access to official sites, repositories and docs; a source URL per claim.
- Workspace: none (nothing writes files or runs commands)
- Models: claude-sonnet-5.5 for every agent
Team (4 agents):
- lead (Research lead, model claude-sonnet-5.5): directs the team; does not produce the work itself; can read web pages and search the web; cannot change your files
  - researcher (Researcher, model claude-sonnet-5.5): can read web pages and search the web; cannot change your files
  - writer (Writer, model claude-sonnet-5.5): cannot change your files
  - factcheck (Independent Fact-Checker, model claude-sonnet-5.5): can read web pages and search the web; cannot change your files
Budget: 22 runs planned (one run = one working session of one agent), your cap is 25; the minimum for one review and rework is 17. Unspent runs come back to you.
  lead starts with 22, hands down researcher 4, writer 3, factcheck 3 and keeps 12 for planning, checking and rework.
If the check still fails after one rework, I'll come back to you with options before spending the reserve (about 5 runs); nothing beyond the 22 planned runs is spent without your OK.
Checking: factcheck reviews the work independently (they did not write it); required changes go back to the author. I then re-check the final result against every success check below.
Deliverable: Competitor analysis with a comparison table and a closing "Where we can win" section marked as our assessment [markdown, max 1500 words]
  Delivered to: ~/deliverables/competitors.md (I copy it there after checking it)
Done when ALL of these hold:
  1. Covers exactly Obsidian, Logseq, Joplin, Trilium and AnyType, and no other app.
  2. At most 1500 words as counted by read.
  3. Contains a comparison table with one row per app and a final section titled "Where we can win" that is marked as our assessment (judgement).
  4. Every sentence with a number, name, version, license, price, date or "no/only/all" is a factual claim and cites the URL of the page that states it; the fact-checker fetched that page and quoted the sentence.
  5. The "Where we can win" section is judgement. It has no citations or new facts and rests only on claims verified elsewhere in the document.
  6. The fact-checker's final coverage line reads 'n of m factual claims verified' with n = m (none wrong, unsupported or not-checkable) and 'each resting on verified facts: yes' for its judgement statements, and the writer applied every required change.
  7. The final report names the path of the deliverable inside the organization, and pastes that coverage line verbatim.
Checkpoints: approval - Approve this plan before anything is created or started; ask before spending beyond the budget; progress - One line when I ask; tell me when it is done. No digging through files; any spend beyond the budget needs your OK.
Nothing is created or started until you approve. Reply 'approve', or tell me what to change.

--- machine marker: the user block ends above; do not show this line or anything below it ---

Details (the full plan, for you; the user need not read it):
# Plan for approval

Goal: Produce a sourced competitor analysis of five self-hosted note-taking apps for a small team choosing one.

Needs as understood:
- Scope: Obsidian, Logseq, Joplin, Trilium and AnyType only; self-hosting, licensing, sync/E2EE, mobile support, extensibility.
- Deliverable: Competitor analysis with a comparison table and a closing "Where we can win" section marked as our assessment [markdown, max 1500 words]
- Quality bar: Every factual claim cites the page that states it; opinions are labelled as judgement, without citations; current facts (versions, licenses) come from the live source.
- Sources / tools: Web access to official sites, repositories and docs; a source URL per claim.
- Workspace: none (no agent writes files or runs commands)
- Model policy: one model for all (claude-sonnet-5.5 for every agent; a cheaper drafting model only if the user asks, with the lead and the fact-check staying strong)
- Review: required

Organization (4 agents):
- lead [manager] Research lead: model=claude-sonnet-5.5, tools=web_fetch,web_search
  - researcher [researcher] Researcher: model=claude-sonnet-5.5, tools=web_fetch,web_search
  - writer [writer] Writer: model=claude-sonnet-5.5, tools=none
  - factcheck [fact-checker] Independent Fact-Checker: model=claude-sonnet-5.5, tools=web_fetch,web_search

Budget: 22 runs planned (your cap: 25), estimate 17 for one pass + one review/rework cycle:
  This is a ceiling: runs the team does not spend come back automatically, agent by agent, with their final reports, until what is left returns to you.
  lead: starts with 22, hands down researcher 4, writer 3, factcheck 3 (each includes its rework/re-check run), keeps 12 (own 7 + slack 5)
  lead/researcher: 4 runs (3 work + 1 rework)
  lead/writer: 3 runs (2 work + 1 rework)
  lead/factcheck: 3 runs (2 work + 1 rework)

Review / verification:
- lead/factcheck checks the work of lead/researcher, lead/writer independently; findings go to their manager, who sends required changes back to the author (nobody edits another agent's file).
- the assistant re-checks the final deliverable against every acceptance criterion before telling you it is done

Deliverable:
- Competitor analysis with a comparison table and a closing "Where we can win" section marked as our assessment (markdown, max 1500 words)
- Final location: ~/deliverables/competitors.md (copied there by the assistant after verification)

First task: to lead: Competitor analysis of five self-hosted note-taking apps
  1. Covers exactly Obsidian, Logseq, Joplin, Trilium and AnyType, and no other app.
  2. At most 1500 words as counted by read.
  3. Contains a comparison table with one row per app and a final section titled "Where we can win" that is marked as our assessment (judgement).
  4. Every sentence with a number, name, version, license, price, date or "no/only/all" is a factual claim and cites the URL of the page that states it; the fact-checker fetched that page and quoted the sentence.
  5. The "Where we can win" section is judgement. It has no citations or new facts and rests only on claims verified elsewhere in the document.
  6. The fact-checker's final coverage line reads 'n of m factual claims verified' with n = m (none wrong, unsupported or not-checkable) and 'each resting on verified facts: yes' for its judgement statements, and the writer applied every required change.
  7. The final report names the path of the deliverable inside the organization, and pastes that coverage line verbatim.

Checkpoints:
- Approval: Approve this plan before anything is created or started; ask before spending beyond the budget.
- Progress: One line when I ask; tell me when it is done. No digging through files.
- Any spend beyond the budget needs your OK.

Warnings (2):
- needs.deliverable.path: no agent can write to <HOME>/deliverables/competitors.md (agents write only inside their own directory or workspace); the assistant must copy the final artifact there and verify it on completion (the plan lists this step)
- needs.deliverable.path: <HOME>/deliverables does not exist; the copy step will create it

Reply 'approve' or tell me what to change.

plan_id: 79ee3ad33ef8
Next: show the PLAN FOR YOU block above to the user exactly as written (a plain-words intro line before it is fine) and wait for their explicit approval. Then apply_org(blueprint=<this exact YAML>, approved=True, plan_id="79ee3ad33ef8"). If you change the blueprint, call propose_org again: the plan_id changes.