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: Sample text
What I understood you need:
- Scope: Sample text
- Your files (read-only): <CWD>/data
- Quality bar: Every number is reproducible from one script and appears with its label in the script's output; no conclusion from a slice under 30 rows.
- Sources: Only the files in needs.inputs; no web.
- Workspace: <CWD>/analysis-work
- Models: claude-sonnet-5.5 for every agent
Team (4 agents):
- lead (Manager, model claude-sonnet-5.5): directs the team; does not produce the work itself; can read files only in <CWD>/analysis-work, <CWD>/data and the organization's own files; can run commands, which are NOT confined: it is told to stay in <CWD>/analysis-work, but nothing enforces that
  - analyst (Data Analyst, model claude-sonnet-5.5): can read files only in <CWD>/analysis-work, <CWD>/data and the organization's own files; can run commands, which are NOT confined: it is told to stay in <CWD>/analysis-work, but nothing enforces that
  - checker (Independent Data Checker, model claude-sonnet-5.5): can read files only in <CWD>/analysis-work, <CWD>/data and the organization's own files; can run commands, which are NOT confined: it is told to stay in <CWD>/analysis-work, but nothing enforces that
  - writer (Writer, model claude-sonnet-5.5): can read files only in <CWD>/data, <CWD>/analysis-work and the organization's own files; cannot change your files
Budget: 23 runs planned (one run = one working session of one agent), your cap is 25; the minimum for one review and rework is 18. Unspent runs come back to you.
  lead starts with 23, hands down analyst 5, checker 3, writer 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 23 planned runs is spent without your OK.
Checking: checker 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: Sample text [markdown, max 1000 words]
  Delivered to: <CWD>/deliverables/briefs.md (I copy it there after checking it)
Done when ALL of these hold:
  1. Uses only <the data file(s)> in the data folder, and the checker confirmed the data files are unchanged (same checksums before and after).
  2. One script in the workspace regenerates every figure in the report; running it twice from a clean state gives identical output.
  3. The script explores <the outcome> against every available column and against every pair of the strongest dimensions (for example reason x region); the report lists the strongest effects with their counts (n and share).
  4. Each number in the report appears together with its label in the script output; the checker verified every label and number pair, not only that the number occurs.
  5. No conclusion is drawn from a slice with fewer than 30 rows; such slices are marked "too small".
  6. At most 1000 words as counted by read; the recommendations are in a section labelled as our assessment (judgement), without figures that are not in the script output.
  7. The checker's line reads 'Figures checked: n of m match' with n = m, and also 'dimensions covered: k of d' with k = d, strongest pairs scanned: yes, reproducible: yes, data unchanged: yes; the writer applied every required change.
Checkpoints: approval - Plan first; ask before any spend beyond the budget; progress - One line when I ask; any spend beyond the budget needs your OK.
Warnings (2):
- <CWD>/analysis-work does not exist yet; apply will create it
- lead, lead/analyst, lead/checker hold shell. kiro cannot confine shell by path: staying inside the workspace (and leaving inputs alone) is instructed in the charter and prompt, not enforced. Built-in read/write ARE confined; only shell is not
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: Sample text

Needs as understood:
- Scope: Sample text
- Deliverable: Sample text [markdown, max 1000 words]
- Quality bar: Every number is reproducible from one script and appears with its label in the script's output; no conclusion from a slice under 30 rows.
- Sources / tools: Only the files in needs.inputs; no web.
- Workspace: <CWD>/analysis-work
- Model policy: one model for all
- Review: required

Organization (4 agents):
- lead [manager] Manager: model=claude-sonnet-5.5, tools=read,shell ws=<CWD>/analysis-work
  Access: kiro read only in <CWD>/analysis-work, <CWD>/data and in the organization's own files (read-only); shell NOT confined (instructed only)
  - analyst [analyst] Data Analyst: model=claude-sonnet-5.5, tools=read,shell ws=<CWD>/analysis-work
    Access: kiro read only in <CWD>/analysis-work, <CWD>/data and in the organization's own files (read-only); shell NOT confined (instructed only)
  - checker [data-checker] Independent Data Checker: model=claude-sonnet-5.5, tools=read,shell ws=<CWD>/analysis-work
    Access: kiro read only in <CWD>/analysis-work, <CWD>/data and in the organization's own files (read-only); shell NOT confined (instructed only)
  - writer [writer] Writer: model=claude-sonnet-5.5, tools=read
    Access: kiro read only in <CWD>/data, <CWD>/analysis-work and in the organization's own files (read-only)

Budget: 23 runs planned (your cap: 25), estimate 18 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 23, hands down analyst 5, checker 3, writer 3 (each includes its rework/re-check run), keeps 12 (own 7 + slack 5)
  lead/analyst: 5 runs (4 work + 1 rework)
  lead/checker: 3 runs (2 work + 1 rework)
  lead/writer: 3 runs (2 work + 1 rework)

Review / verification:
- lead/checker checks the work of lead/analyst, 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:
- Sample text (markdown, max 1000 words)
- Final location: <CWD>/deliverables/briefs.md (copied there by the assistant after verification)

First task: to lead: Sample text
  1. Uses only <the data file(s)> in the data folder, and the checker confirmed the data files are unchanged (same checksums before and after).
  2. One script in the workspace regenerates every figure in the report; running it twice from a clean state gives identical output.
  3. The script explores <the outcome> against every available column and against every pair of the strongest dimensions (for example reason x region); the report lists the strongest effects with their counts (n and share).
  4. Each number in the report appears together with its label in the script output; the checker verified every label and number pair, not only that the number occurs.
  5. No conclusion is drawn from a slice with fewer than 30 rows; such slices are marked "too small".
  6. At most 1000 words as counted by read; the recommendations are in a section labelled as our assessment (judgement), without figures that are not in the script output.
  7. The checker's line reads 'Figures checked: n of m match' with n = m, and also 'dimensions covered: k of d' with k = d, strongest pairs scanned: yes, reproducible: yes, data unchanged: yes; the writer applied every required change.

Checkpoints:
- Approval: Plan first; ask before any spend beyond the budget.
- Progress: One line when I ask.
- Any spend beyond the budget needs your OK.

Warnings (4):
- needs.workspace: <CWD>/analysis-work does not exist yet; apply will create it
- agents: lead, lead/analyst, lead/checker hold shell. kiro cannot confine shell by path: staying inside the workspace (and leaving inputs alone) is instructed in the charter and prompt, not enforced. Built-in read/write ARE confined; only shell is not
- needs.deliverable.path: no agent can write to <CWD>/deliverables/briefs.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: <CWD>/deliverables does not exist; the copy step will create it

Reply 'approve' or tell me what to change.

plan_id: <PLAN_ID>
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="<PLAN_ID>"). If you change the blueprint, call propose_org again: the plan_id changes.