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
- Quality bar: Tests pass from a clean checkout; no network use at runtime.
- Workspace: <CWD>/proj
- Tests / packaging / commits: tests: pytest, at least one test per acceptance criterion; packaging: uv with a pyproject.toml; commits: local commits per feature; never push
- 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 in <CWD>/proj and the organization's own files; changes files only in <CWD>/proj; can run commands, which are NOT confined: it is told to stay in <CWD>/proj, but nothing enforces that
  - dev (Engineer, model claude-sonnet-5.5): can read files in <CWD>/proj and the organization's own files; changes files only in <CWD>/proj; can run commands, which are NOT confined: it is told to stay in <CWD>/proj, but nothing enforces that
  - qa (Tester, model claude-sonnet-5.5): can read files in <CWD>/proj and the organization's own files; changes files only in <CWD>/proj; can run commands, which are NOT confined: it is told to stay in <CWD>/proj, but nothing enforces that
  - cr (Code Reviewer, model claude-sonnet-5.5): can read files only in <CWD>/proj and the organization's own files; can run commands, which are NOT confined: it is told to stay in <CWD>/proj, but nothing enforces that
Budget: 23 runs planned (one run = one working session of one agent), your cap is 30; the minimum for one review and rework is 18. Unspent runs come back to you.
  lead starts with 23, hands down dev 5, qa 3, cr 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: qa, cr review 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 [python package]
  Delivered to: the workspace <CWD>/proj (the team works and commits there)
Done when ALL of these hold:
  1. `uv run pytest -q` passes with at least 5 tests.
  2. Sample text
  3. The tester ran the software against every criterion and the engineer applied every required change.
  4. Work is committed locally in the workspace and nothing was pushed.
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):
- lead, lead/dev, lead/qa, lead/cr 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
- 'Sample text' is not checkable; state the exact number, section, format or path that decides pass/fail
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 [python package]
- Quality bar: Tests pass from a clean checkout; no network use at runtime.
- Sources / tools: (not specified)
- Workspace: <CWD>/proj
- Tests / packaging / commits: tests: pytest, at least one test per acceptance criterion; packaging: uv with a pyproject.toml; commits: local commits per feature; never push
- Model policy: one model for all
- Review: required

Organization (4 agents):
- lead [manager] Manager: model=claude-sonnet-5.5, tools=read,shell,write ws=<CWD>/proj
  Access: kiro write only in <CWD>/proj; kiro read only in <CWD>/proj and in the organization's own files (read-only); shell NOT confined (instructed only)
  - dev [engineer] Engineer: model=claude-sonnet-5.5, tools=read,shell,write ws=<CWD>/proj
    Access: kiro write only in <CWD>/proj; kiro read only in <CWD>/proj and in the organization's own files (read-only); shell NOT confined (instructed only)
  - qa [tester] Tester: model=claude-sonnet-5.5, tools=read,shell,write ws=<CWD>/proj
    Access: kiro write only in <CWD>/proj; kiro read only in <CWD>/proj and in the organization's own files (read-only); shell NOT confined (instructed only)
  - cr [code-reviewer] Code Reviewer: model=claude-sonnet-5.5, tools=read,shell ws=<CWD>/proj
    Access: kiro read only in <CWD>/proj and in the organization's own files (read-only); shell NOT confined (instructed only)

Budget: 23 runs planned (your cap: 30), 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 dev 5, qa 3, cr 3 (each includes its rework/re-check run), keeps 12 (own 7 + slack 5)
  lead/dev: 5 runs (4 work + 1 rework)
  lead/qa: 3 runs (2 work + 1 rework)
  lead/cr: 3 runs (2 work + 1 rework)

Review / verification:
- lead/qa, lead/cr check the work of lead/dev 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 (python package)
- Final location: inside the organization (no path given)

First task: to lead: Sample text
  1. `uv run pytest -q` passes with at least 5 tests.
  2. Sample text
  3. The tester ran the software against every criterion and the engineer applied every required change.
  4. Work is committed locally in the workspace and nothing was pushed.

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):
- agents: lead, lead/dev, lead/qa, lead/cr 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
- task.acceptance[2]: 'Sample text' is not checkable; state the exact number, section, format or path that decides pass/fail

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.