subagent-driven-development

Subagent-Driven Development

Execute plan by dispatching a fresh implementer subagent per task, a task review (spec compliance + code quality) after each, and a broad whole-branch review at the end.

Why subagents: You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit your session's context or history — you construct exactly what they need. This also preserves your own context for coordination work.

Core principle: Fresh subagent per task + task review (spec + quality) + broad final review = high quality, fast iteration

Narration: between tool calls, narrate at most one short line — the

ledger and the tool results carry the record.

Continuous execution: Do not pause to check in with your human partner between tasks. Execute all tasks from the plan without stopping. The only reasons to stop are the four named below, or all tasks complete. "Should I continue?" prompts and progress summaries waste their time — they asked you to execute the plan, so execute it.

Rulings, not stalls. A running plan does not wait on a human. Conflicts,

ambiguities, plan defects, a cap you would have asked to exceed — decide

them. The spec is the binding authority, the plan is its argument, and your

judgment settles what neither answers. Record every decision in the ledger as

Ruling: <what you decided> — <why> — <what it costs if wrong>, and keep

going. A wrong ruling costs rework your human partner can see and undo; a

session parked on a question costs their whole day and buys nothing.

Four things stop you, and only these: an irreversible or destructive

operation; a security-sensitive action; a side effect outside this worktree

that norms say you ask about first (a merge, a push to a shared branch, a

publish); and a plan so broken that every path forward is a guess. For those,

stop and ask.

When to Use

digraph when_to_use {
    "Have implementation plan?" [shape=diamond];
    "Tasks mostly independent?" [shape=diamond];
    "Partner chose inline, or no subagent tool?" [shape=diamond];
    "subagent-driven-development" [shape=box];
    "executing-plans" [shape=box];
    "Manual execution or brainstorm first" [shape=box];

    "Have implementation plan?" -> "Tasks mostly independent?" [label="yes"];
    "Have implementation plan?" -> "Manual execution or brainstorm first" [label="no"];
    "Tasks mostly independent?" -> "Partner chose inline, or no subagent tool?" [label="yes"];
    "Tasks mostly independent?" -> "Manual execution or brainstorm first" [label="no - tightly coupled"];
    "Partner chose inline, or no subagent tool?" -> "executing-plans" [label="yes"];
    "Partner chose inline, or no subagent tool?" -> "subagent-driven-development" [label="no"];
}

vs. Executing Plans (inline):

• Fresh subagent per task (no context pollution) instead of one context doing every task
• Review after each task (spec compliance + code quality) instead of only at the end
• Costs a fresh context per task and per review; inline costs one context plus one final reviewer
• Both run in this session, share the same plan workspace and ledger, and never pause between tasks

The Process

digraph process {
    rankdir=TB;

    subgraph cluster_per_task {
        label="Per Task";
        "Dispatch implementer subagent (./implementer-prompt.md)" [shape=box];
        "Implementer asks questions?" [shape=diamond];
        "Answer questions, provide context" [shape=box];
        "Implementer implements, tests, commits, self-reviews" [shape=box];
        "Generate review package, dispatch task reviewer (./task-reviewer-prompt.md)" [shape=box];
        "Spec ✅ and quality approved?" [shape=diamond];
        "Fix loop: read references/fix-loop.md before every round" [shape=box];
        "Append completion to ledger, mark todo complete" [shape=box];
    }

    "Setup: worktree, ledger check, read plan, pre-flight review" [shape=box];
    "More tasks remain?" [shape=diamond];
    "Final review and finish: read references/final-review.md" [shape=box];
    "Final review clean: delete this plan's workspace" [shape=box];
    "Use superpowers:finishing-a-development-branch" [shape=box style=filled fillcolor=lightgreen];

    "Setup: worktree, ledger check, read plan, pre-flight review" -> "Dispatch implementer subagent (./implementer-prompt.md)";
    "Dispatch implementer subagent (./implementer-prompt.md)" -> "Implementer asks questions?";
    "Implementer asks questions?" -> "Answer questions, provide context" [label="yes"];
    "Answer questions, provide context" -> "Implementer implements, tests, commits, self-reviews";
    "Implementer asks questions?" -> "Implementer implements, tests, commits, self-reviews" [label="no"];
    "Implementer implements, tests, commits, self-reviews" -> "Generate review package, dispatch task reviewer (./task-reviewer-prompt.md)";
    "Generate review package, dispatch task reviewer (./task-reviewer-prompt.md)" -> "Spec ✅ and quality approved?";
    "Spec ✅ and quality approved?" -> "Append completion to ledger, mark todo complete" [label="yes"];
    "Spec ✅ and quality approved?" -> "Fix loop: read references/fix-loop.md before every round" [label="no"];
    "Fix loop: read references/fix-loop.md before every round" -> "Append completion to ledger, mark todo complete" [label="addressed, or parked at the cap"];
    "Append completion to ledger, mark todo complete" -> "More tasks remain?";
    "More tasks remain?" -> "Dispatch implementer subagent (./implementer-prompt.md)" [label="yes"];
    "More tasks remain?" -> "Final review and finish: read references/final-review.md" [label="no"];
    "Final review and finish: read references/final-review.md" -> "Final review clean: delete this plan's workspace";
    "Final review clean: delete this plan's workspace" -> "Use superpowers:finishing-a-development-branch";
}

Setup

Ensure the work happens in an isolated workspace: use

superpowers:using-git-worktrees to create one or verify the existing one.

Never start implementation on a main/master branch without your human

partner's explicit consent.

Conversation memory does not survive compaction. In real sessions,

controllers that lost their place have re-dispatched entire completed task

sequences — the single most expensive failure observed. Track progress in

a ledger file, not only in todos.

• Each plan owns a workspace: at skill start, run this skill's

bash scripts/sdd-workspace PLAN_FILE — it prints the plan's git-ignored

directory (under <repo-root>/.superpowers/sdd/), home to

every artifact for THIS plan: ledger, briefs, reports, review packages.

Another plan's directory is never yours to read or write.

• Check for this plan's ledger at <workspace>/progress.md. If one exists,

read references/resuming.md before anything

else: it says whose ledger it is and where to resume.

• Create the ledger with its identity as the first line:

# SDD ledger — plan: <plan file path>.

• The ledger is your recovery map: the commits it names exist in git even

when your context no longer remembers creating them. After compaction,

trust the ledger and git log over your own recollection.

• git clean -fdx will destroy the workspace (it's git-ignored scratch); if

that happens, recover from git log.

Read the plan once, note its context and Global Constraints, and create a

todo per task. If the plan names a Spec, read that too: the spec is the

authority the plan argues from, and conflicts inside the plan resolve

against it. A plan with no reachable spec gets a ledger note saying so —

rulings made without one are provisional.

Before dispatching Task 1, read references/preflight.md

and run the conflict scan it describes. Its table and rulings go in the

ledger.

Model Selection

Use the least powerful model that can handle each role to conserve cost and increase speed.

Mechanical implementation tasks (isolated functions, clear specs, 1-2 files): use a fast, cheap model. Most implementation tasks are mechanical when the plan is well-specified.

Integration and judgment tasks (multi-file coordination, pattern matching, debugging): use a standard model.

Architecture and design tasks: use the most capable available model.

The final whole-branch review is one of these — dispatch it on the most

capable available model, not the session default.

Review tasks: choose the model with the same judgment, scaled to the

diff's size, complexity, and risk. A small mechanical diff does not need the

most capable model; a subtle concurrency change does. Scoped re-reviews of

small fix diffs take a cheap-to-mid tier.

Fix-loop escalation (rounds 4-5): use a model at least one tier above

the implementer that got stuck.

Always specify the model explicitly when dispatching a subagent. An

omitted model inherits your session's model — often the most capable and

most expensive — which silently defeats this section.

Turn count beats token price. Wall-clock and context cost scale with how

many turns a subagent takes, and the cheapest models routinely take 2-3× the

turns on multi-step work — costing more overall. Use a mid-tier model as the

floor for reviewers and for implementers working from prose descriptions.

When the task's plan text contains the complete code to write, the

implementation is transcription plus testing: use the cheapest tier for

that implementer. Single-file mechanical fixes also take the cheapest tier.

Task complexity signals (implementation tasks):

• Touches 1-2 files with a complete spec → cheap model
• Touches multiple files with integration concerns → standard model
• Requires design judgment or broad codebase understanding → most capable model

The Task Loop

Small same-shape work: when the plan lists several small edits of the

same kind across files, read references/batching.md

before dispatching them.

Everything you paste into a dispatch prompt — and everything a subagent

prints back — stays resident in your context for the rest of the session

and is re-read on every later turn. Hand artifacts over as files.

Waiting on dispatched subagents: never poll a wait interface with

short timeouts, and never sit in one silent, open-ended wait either.

While you have local work — ledger updates, packaging the next review,

reading reports — keep working; child results arrive on their own.

When you are genuinely idle, wait in bounded stretches (five to ten

minutes, where your platform allows), and between stretches post one

line of status and reconcile your live children: list them, and chase

any that finished without reporting. A bounded stretch keeps nearly

all of a long wait's efficiency while guaranteeing a stuck or lost

child is noticed within minutes, not at the end of the session.

1. Dispatch the implementer

Record BASE (git rev-parse HEAD) before dispatching — the review package

and fix-round diffs need it.

• Task brief: before dispatching an implementer, run this skill's

bash scripts/task-brief PLAN_FILE N — it extracts the task's full text to a

uniquely named file and prints the path. Compose the dispatch so the

brief stays the single source of

requirements. Your dispatch should contain: (1) one line on where this

task fits in the project; (2) the brief path, introduced as "read this

first — it is your requirements, with the exact values to use verbatim";

(3) interfaces and decisions from earlier tasks that the brief cannot

know; (4) your resolution of any ambiguity you noticed in the brief;

(5) the report-file path and report contract. Exact values (numbers,

magic strings, signatures, test cases) appear only in the brief. Never

make a subagent read the whole plan file.

• Report file: name the implementer's report file after the brief

(brief …/task-N-brief.md → report …/task-N-report.md) and put it in

the dispatch prompt. The implementer writes the full report there and

returns only status, commits, a one-line test summary, and concerns.

• A dispatch prompt describes one task, not the session's history. Do not

paste accumulated prior-task summaries ("state after Tasks 1-3") into

later dispatches — a real session's dispatch hit 42k chars of which 99%

was pasted history. A fresh subagent needs its task, the interfaces it

touches, and the global constraints. Nothing else.

• The dispatch carries the no-subagents contract (it is in the

implementer template): the implementer never dispatches subagents —

not helpers, and never a reviewer. Review arrives from you, after the

report. In real sessions, every reviewer a worker spawned duplicated

the task review the controller dispatched anyway — a full extra

review seat per task.

• If an earlier task parked a finding in the area this task touches, carry

a pointer to that ledger entry in the dispatch.

• Record the implementer's agent identity from the dispatch result —

fix-loop rounds 1-3 resume this agent.

• Never dispatch multiple implementation subagents in parallel (conflicts).

Template: implementer-prompt.md

2. Handle the report

Implementer subagents report one of four statuses. Handle each appropriately:

DONE: Generate the review package (bash scripts/review-package PLAN_FILE BASE HEAD, from this skill's directory — it prints the unique file path it wrote; BASE is the commit you recorded before dispatching the implementer — never HEAD~1, which silently drops all but the last commit of a multi-commit task), then dispatch the task reviewer with the printed path.

Any other status (DONE_WITH_CONCERNS, NEEDS_CONTEXT, BLOCKED): read

references/handling-reports.md and follow

it, every time you get one.

If the implementer asks questions — before starting or mid-task — answer

clearly and completely, provide additional context if needed, and don't

rush it into implementation.

3. Review the task

Per-task reviews are task-scoped gates. The broad review happens once, at the

final whole-branch review. Never skip the task review, and never accept a

report missing either verdict — spec compliance AND task quality are both

required. Implementer self-review never replaces the task review; both are

needed.

• Hand the reviewer its diff as a file: run this skill's

bash scripts/review-package PLAN_FILE BASE HEAD and pass the reviewer the file path

it prints (or, without bash: git log --oneline, git diff --stat,

and git diff -U10 for the range, redirected to one uniquely named

file). The output never enters your own context, and the reviewer sees

the commit list, stat summary, and full diff with context in one Read

call. Use the BASE you recorded before dispatching the implementer —

never HEAD~1, which silently truncates multi-commit tasks. Never

dispatch a task reviewer without a diff file.

• Reviewer inputs: the task reviewer gets three paths — the same brief

file, the report file, and the review package — plus the global

constraints that bind the task.

• The global-constraints block you hand the reviewer is its attention

lens. Copy the binding requirements verbatim from the plan's Global

Constraints section or the spec: exact values, exact formats, and the

stated relationships between components ("same layout as X", "matches

Y"). The reviewer's template already carries the process rules (YAGNI,

test hygiene, review method) — the constraints block is for what THIS

project's spec demands.

• Do not add open-ended directives like "check all uses" or "run race tests

if useful" without a concrete, task-specific reason

• Do not ask a reviewer to re-run tests the implementer already ran on the

same code — the implementer's report carries the test evidence

• Do not pre-judge findings for the reviewer — never instruct a reviewer to

ignore or not flag a specific issue. If you believe a finding would be a

false positive, let the reviewer raise it and adjudicate it in the review

loop. If the prompt you are writing contains "do not flag," "don't treat X

as a defect," "at most Minor," or "the plan chose" — stop: you are

pre-judging, usually to spare yourself a review loop.

If the reviewer reports "⚠️ Cannot verify from diff" items, read

references/cannot-verify.md before you mark

the task complete.

Template: task-reviewer-prompt.md

4. The fix loop

The loop triggers when the review reports spec ❌, any Critical or Important

finding, or a ⚠️ item you confirmed as a real gap.

When it triggers, read references/fix-loop.md and

follow it. Read it again before every round, even if you read it earlier in

this session: it holds the round cap, the breaker, and the ledger line each

round writes, and your memory of it does not survive compaction.

5. Complete the task

When the review comes back clean — or every open finding is parked with a

ruling at the cap — append the completion line to the ledger in the same

message as your other bookkeeping:

• Task <N>: complete (commits <base7>..<head7>, review clean)
• Task <N>: complete (commits <base7>..<head7>, <K> parked) after a

tripped breaker

Then mark the todo complete and move on. Never move to the next task while

the review has open Critical/Important issues that are neither fixed nor

parked-with-ruling at the cap.

Final Review

When every task is complete, read

references/final-review.md and follow it. It

covers the whole-branch review, its single fix wave, and how you finish.

Common Rationalizations

| Excuse | Reality |

|--------|---------|

| "Close enough on spec compliance" | Reviewer found spec gaps = not done. Fix or hit the cap and adjudicate — those are the only exits. |

| "I'll fix it myself, dispatching is overhead" | Controller fixes pollute your context and skip review. Resume the implementer. |

| "One more round will converge" | Past the cap, rounds don't converge — the failure is structural. Adjudicate and route. |

| "The reviewer will just find something new anyway" | Scoped re-reviews verify fixes; they cannot wander. New findings on untouched code go to the ledger, not the loop. |

| "This finding is obviously wrong, I'll drop it" | You adjudicate only at the cap, and every ruling is a ledger entry. Silent discards are forbidden. |

| "The fix was small, skip the re-review" | Unreviewed fixes are how regressions land. Every round ends with a scoped re-review. |

| "Reviews slow the loop down" | The loop without reviews is just unverified churn. Reviews are the loop's brakes and steering. |

| "Ledger bookkeeping is overhead" | The ledger is what survives compaction. Controllers without one have re-dispatched entire completed task sequences. |

| "The implementer spawned its own reviewer — free extra assurance" | It's a duplicate seat reviewing the same diff; the task review is the gate. A worker-spawned reviewer is a defect to flag, not rigor. |