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

DRAFT - NOT READY (it has errors: fix the blueprint and propose again; do not show this to the user)
Goal: <One paragraph: what document the organization writes from the user's files, and for whom.>
What I understood you need:
- Scope: <What the document covers and what it leaves out, in the user's words.>
- Your files (read-only): <CWD>/<folder-with-your-files>
- Quality bar: Every statement comes from the input files; where the files disagree or are silent, the document says so.
- Sources: Only the files in needs.inputs; no web.
- Workspace: none (nothing writes files or runs commands)
- 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 no files outside the organization; cannot change your files
  - reader (Reader of the user's files, model claude-sonnet-5.5): can read no files outside the organization; cannot change your files
  - writer (Writer, model claude-sonnet-5.5): cannot change your files
  - reviewer (Independent Reviewer, model claude-sonnet-5.5): can read no files outside the organization; cannot change your files
Budget: up to 19 runs per request (one run = one working session of one agent), your cap per request is 25; the minimum for one review and rework is 15. Unspent runs come back to you.
  lead starts with 19, hands down reader 3, writer 3, reviewer 2 and keeps 11 for planning, checking and rework.
If a check still fails after one rework, I'll come back to you with options before spending the reserve; nothing beyond a request's budget is spent without your OK.
Checking: reviewer 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 service check below.
Services (kept ready, requested whenever you want):
- <service-name>: <One line saying what one request delivers>
  You provide: (see the errors)
  Each request: up to 19 runs
  Checks:
    1. Covers <the topic of the request> and nothing else.
    2. At most 1500 words as counted by read.
    3. Every statement is traceable to a named input file, and gaps or conflicts between files are listed in a final section titled "Open questions".
    4. The reviewer's report shows every criterion met (criteria met: n of m with n = m), and the writer applied every required change.
  Delivered to: <CWD>/deliverables/<name> (I copy each result there after checking it)
After each request the lead records lessons; before the next one it reviews them with your feedback and may improve how the team works (its playbook). It cannot change these checks: only you can, through me.
Nothing runs until you ask for a request: approving only creates the team and the services.
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 (3):
- has built-in read but no workspace or inputs, so it can read nothing outside the organization; set needs.inputs or needs.workspace if it must read files
- has built-in read but no workspace or inputs, so it can read nothing outside the organization; set needs.inputs or needs.workspace if it must read files
- has built-in read but no workspace or inputs, so it can read nothing outside the organization; set needs.inputs or needs.workspace if it must read files
Errors (3):
- needs.inputs: input <CWD>/<folder-with-your-files> does not exist; inputs are read-only sources and must be there already
- services[<service-name>]: invalid service name '<service-name>': use lowercase letters, digits and dashes (max 32, starting with a letter), e.g. weekly-brief
- services[<service-name>].inputs: input name must be lowercase letters, digits and underscores, starting with a letter (max 32): '<input-name>'
Cannot apply yet.

--- 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: <One paragraph: what document the organization writes from the user's files, and for whom.>

Needs as understood:
- Scope: <What the document covers and what it leaves out, in the user's words.>
- Deliverable: per service (see Services below)
- Quality bar: Every statement comes from the input files; where the files disagree or are silent, the document says so.
- Sources / tools: Only the files in needs.inputs; no web.
- Workspace: none (no agent writes files or runs commands)
- Model policy: one model for all
- Review: required

Organization (4 agents):
- lead [manager] Manager: model=claude-sonnet-5.5, tools=read
  Access: kiro read only in the organization's own files (read-only)
  - reader [custom] Reader of the user's files: model=claude-sonnet-5.5, tools=read
    Access: kiro read only in the organization's own files (read-only)
  - writer [writer] Writer: model=claude-sonnet-5.5, tools=none
  - reviewer [reviewer] Independent Reviewer: model=claude-sonnet-5.5, tools=read
    Access: kiro read only in the organization's own files (read-only)

Budget per request (your cap: 25), estimate 15 for one pass + one review/rework cycle:
  A ceiling: runs the team does not spend come back automatically with the final report of each request.
  service <service-name>: 19 runs per request
    lead: starts with 19, hands down reader 3, writer 3, reviewer 2 (each includes its rework/re-check run), keeps 11 (own 7 + slack 4)
    lead/reader: 3 runs (2 work + 1 rework)
    lead/writer: 3 runs (2 work + 1 rework)
    lead/reviewer: 2 runs (1 work + 1 rework)

Review / verification:
- lead/reviewer checks the work of lead/reader, 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:
- per service (see Services below)

Services (1), offered by lead and defined by root (the contract: only root can change it):
- <service-name>: <One line saying what one request delivers>
  inputs: (see the errors)
  budget: 19 runs per request
  deliverable: <What one request produces, e.g. one markdown section for the topic> [markdown, max 1500 words]; delivered to: <CWD>/deliverables/<name> (I copy each result there after checking it)
  acceptance (the contract, travels with every request):
    1. Covers <the topic of the request> and nothing else.
    2. At most 1500 words as counted by read.
    3. Every statement is traceable to a named input file, and gaps or conflicts between files are listed in a final section titled "Open questions".
    4. The reviewer's report shows every criterion met (criteria met: n of m with n = m), and the writer applied every required change.
  playbook v1: generated from the team (steps, budget plan, pitfalls):
    ## Steps
    1. Read the request in your prompt: its inputs, every acceptance criterion and the deliverable. The criteria come from the contract and can only be met, never changed; copy the relevant ones verbatim into every task you delegate.
    2. Delegate to `reader` (Reader of the user's files) with `budget=3`: its part of the request, with the criteria it must meet. On this first run delegate only the steps that need nothing from a teammate.
    3. When the previous result is in, read its artifact yourself, then delegate to `writer` (Writer) with `budget=3`, naming the artifact it builds on. Never delegate a step before its inputs exist, and send no status messages: results wake you.
    4. When the work exists, delegate to `reviewer` (Independent Reviewer) with `budget=2` to check the final file independently against every criterion. It reports findings and required changes to you and never edits the author's file.
    5. If a check fails: send the required changes, quoted verbatim, to the AUTHOR of the failing file (`delegate(to=<author>, revises=<that author's task id>, budget=1)`; for the deliverable usually `writer`), then have the checker re-check that same file (`delegate(to=<checker>, revises=<the checker's task id>)`). One rework and one re-check; if it still fails, report `blocked` with options and the checker's final line instead of starting another cycle.
    6. Read the final artifact yourself and check it against EVERY criterion of the request, quoting counts from your own `read` output, and paste the checker's final coverage line verbatim.
    7. Report: `done` only if every criterion is met (else `blocked` with the deviation and a recommended decision). Name the deliverable's path (the assistant copies it to <CWD>/deliverables/<name>) and pass `lessons`: 1-3 lines for the next request - what worked, what to change in this playbook, and the evidence (runs used, rework, review findings).
    
    ## Budget plan
    Request budget: 19 runs (the contract's). Hand down no more than this up front, each with `budget=` set explicitly:
    - reader: 3 runs (2 work + 1 rework or re-check)
    - writer: 3 runs (2 work + 1 rework or re-check)
    - reviewer: 2 runs (1 work + 1 rework or re-check)
    - you (lead): keep 11 runs: your own 7 (plan, process each result, final check, report, one rework cycle) and 4 of slack.
    Unspent runs return to your parent with your final report.
    
    ## Pitfalls
    none yet: add them from lessons and feedback
After each request the lead records lessons; before the next one it reviews them with your feedback and may improve how the team works (its playbook). It cannot change these checks: only you can, through me.
No first task: nothing runs until you ask for a request (request(service, inputs), then start()).

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 (5):
- agents[lead]: has built-in read but no workspace or inputs, so it can read nothing outside the organization; set needs.inputs or needs.workspace if it must read files
- agents[lead/reader]: has built-in read but no workspace or inputs, so it can read nothing outside the organization; set needs.inputs or needs.workspace if it must read files
- agents[lead/reviewer]: has built-in read but no workspace or inputs, so it can read nothing outside the organization; set needs.inputs or needs.workspace if it must read files
- services[<service-name>].deliverable.path: no agent can write to <CWD>/deliverables/<name> (agents write only inside their own directory or workspace); the assistant must copy each result there and verify it (the plan lists this step)
- services[<service-name>].deliverable.path: <CWD>/deliverables does not exist; the copy step will create it

Errors (3) - must be fixed before this can be applied:
- needs.inputs: input <CWD>/<folder-with-your-files> does not exist; inputs are read-only sources and must be there already
- services[<service-name>]: invalid service name '<service-name>': use lowercase letters, digits and dashes (max 32, starting with a letter), e.g. weekly-brief
- services[<service-name>].inputs: input name must be lowercase letters, digits and underscores, starting with a letter (max 32): '<input-name>'

Cannot apply yet: tell me what to change.

plan_id: none (the blueprint has errors). Fix them and call propose_org again; do not ask the user to approve this.