subagent-driven-development

<!-- Coacus adaptation of a Superpowers workflow (MIT). Upstream: https://github.com/obra/superpowers @ 5bf4e78011075bcfc0dc295f0724994cd123ee71 Process artifacts are written under docs/temp/. Conventions: ../using-coacus/references/coacus-process-conventions.md --> # 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 ```dot 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 ```dot 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]; "Finding conflicts with plan text?" [shape=diamond]; "Rule on the conflict, ledger the ruling" [shape=box]; "Fix round R of 5: R≤3 resume implementer; R≥4 fresh implementer" [shape=box]; "Dispatch scoped re-review (./re-review-prompt.md)" [shape=box]; "All findings addressed?" [shape=diamond]; "R = 5?" [shape=diamond]; "Adjudicate each open finding" [shape=box]; "Any load-bearing finding?" [shape=diamond]; "Rule and continue; stop only if every path forward is a guess" [shape=box]; "Park findings in ledger with rulings" [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]; "Dispatch final code reviewer (../requesting-code-review/code-reviewer.md)" [shape=box]; "Final findings? ONE fix dispatch, one scoped re-review, adjudicate residuals" [shape=box]; "Final review clean: delete this plan's workspace" [shape=box]; "Use 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?" -> "Finding conflicts with plan text?" [label="no"]; "Finding conflicts with plan text?" -> "Rule on the conflict, ledger the ruling" [label="yes"]; "Rule on the conflict, ledger the ruling" -> "Fix round R of 5: R≤3 resume implementer; R≥4 fresh implementer"; "Finding conflicts with plan text?" -> "Fix round R of 5: R≤3 resume implementer; R≥4 fresh implementer" [label="no"]; "Fix round R of 5: R≤3 resume implementer; R≥4 fresh implementer" -> "Dispatch scoped re-review (./re-review-prompt.md)"; "Dispatch scoped re-review (./re-review-prompt.md)" -> "All findings addressed?"; "All findings addressed?" -> "Append completion to ledger, mark todo complete" [label="yes"]; "All findings addressed?" -> "R = 5?" [label="no"]; "R = 5?" -> "Fix round R of 5: R≤3 resume implementer; R≥4 fresh implementer" [label="no - next round"]; "R = 5?" -> "Adjudicate each open finding" [label="yes - breaker trips"]; "Adjudicate each open finding" -> "Any load-bearing finding?"; "Any load-bearing finding?" -> "Rule and continue; stop only if every path forward is a guess" [label="yes"]; "Any load-bearing finding?" -> "Park findings in ledger with rulings" [label="no"]; "Park findings in ledger with rulings" -> "Append completion to ledger, mark todo complete"; "Append completion to ledger, mark todo complete" -> "More tasks remain?"; "More tasks remain?" -> "Dispatch implementer subagent (./implementer-prompt.md)" [label="yes"]; "More tasks remain?" -> "Dispatch final code reviewer (../requesting-code-review/code-reviewer.md)" [label="no"]; "Dispatch final code reviewer (../requesting-code-review/code-reviewer.md)" -> "Final findings? ONE fix dispatch, one scoped re-review, adjudicate residuals"; "Final findings? ONE fix dispatch, one scoped re-review, adjudicate residuals" -> "Final review clean: delete this plan's workspace"; "Final review clean: delete this plan's workspace" -> "Use finishing-a-development-branch"; } ``` ## Setup Ensure the work happens in an isolated workspace: use 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 `python3 scripts/sdd-workspace.py PLAN_FILE` — it prints the plan's git-ignored directory (under `<repo-root>/.coacus/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 its first line names your plan file, tasks with a `Task <N>: complete` line are DONE — do not re-dispatch them; resume at the first task without one. A task whose last line is a fix round is mid-loop: resume the loop at the next round. A ledger whose first line names a different plan file — or a stray ledger at the old flat path `.coacus/sdd/progress.md` — is another plan's progress: leave it in place and start your own, fresh. - 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, scan the plan once for conflicts, writing down what you checked as you check it: - tasks that contradict each other or the plan's Global Constraints - anything the plan explicitly mandates that the review rubric treats as a defect (a test that asserts nothing, verbatim duplication of a logic block) The scan's output is a table, not a verdict. One row for every pair of tasks that share a file or an interface: the two tasks, what one produces against what the other consumes, and what you found. One row for every task: whether its own text agrees with itself — the tests it specifies against the code it specifies, the files it creates against the files it later touches. "The scan is clean" without those rows is not a scan you ran. Write the table to the ledger. Rule on everything you find before execution begins — each finding against the plan text that mandates it — and record each ruling in the ledger. If the scan is clean, proceed without comment. Rule on each conflict it surfaces — the spec is the binding authority, the plan is its argument — record the ruling beside its row, and dispatch Task 1. The review loop remains the net for conflicts that only emerge from implementation. ## Model Selection Inherit the session model by default. Specify a model only if the user explicitly requests one and the harness permits it. A blocked task calls for better context, narrower scope, a fresh implementer or human escalation; never override model selection policy to retry it. ## The Task Loop Batch small, repetitive same-shape edits into one dispatch brief. For judgment, tests, or isolated review surfaces, use one dispatch per task. Hand artifacts over as file paths rather than pasting them into prompts to preserve context. For detailed contracts, see [Task Loop Mechanics](references/task-loop-mechanics.md). ### 1. Dispatch the implementer Record BASE (`git rev-parse HEAD`). Run `python3 scripts/task-brief.py PLAN_FILE N` to generate the task brief. If the plan session produced an agent roster (`writing-plans` → Agent Roster), dispatch the roster agent assigned to this task; otherwise use the generic implementer. Dispatch the implementer subagent with: (1) project placement, (2) brief path as binding authority, (3) necessary interface decisions, and (4) the dedicated report path (`…/task-N-report.md`). Never make subagents read the full plan file, and enforce the no-subagents rule. Template: [implementer-prompt.md](implementer-prompt.md) ### 2. Handle the report Implementers report one of four statuses: - **DONE:** Generate review package (`python3 scripts/review-package.py PLAN_FILE BASE HEAD`) and dispatch the task reviewer. - **DONE_WITH_CONCERNS:** Inspect concerns. Address correctness issues immediately; note observations and proceed to review. - **NEEDS_CONTEXT:** Supply missing context and re-dispatch. - **BLOCKED:** Assess the blocker. Provide context, break down the task, or ledger plan corrections. Never force retry without changes. ### 3. Review the task Every task requires two verdicts: spec compliance AND task quality. Self-review never replaces task review. - Run `python3 scripts/review-package.py PLAN_FILE BASE HEAD` and hand the reviewer the resulting diff package, brief path, report path, and project Global Constraints. - Never dispatch without a diff package or pre-judge findings. - Resolve any "⚠️ Cannot verify from diff" items; if verified as real gaps, route them to the fix loop. Template: [task-reviewer-prompt.md](task-reviewer-prompt.md) ### 4. The fix loop Triggered when the review reports spec ❌, Critical/Important findings, or verified gaps. Up to 5 rounds maximum per task: - **Deferred minors:** Record Minor findings in the ledger (`Task <N>: minor (deferred): <one-liner>`) for final whole-branch triage; they do not enter the loop. - **Plan conflicts:** Adjudicate against the spec, ledger the ruling, and direct the fix. - **Rounds 1–3:** Resume the existing implementer with the open findings list. - **Rounds 4–5:** Dispatch a fresh implementer with full failure history. - **Re-review:** Scoped re-review via `python3 scripts/review-package.py PLAN_FILE FIX_BASE HEAD` with [re-review-prompt.md](re-review-prompt.md). - **The Breaker:** At round 5 cap, stop dispatching. Adjudicate each open finding (park with ruling, or rule on load-bearing items). ### 5. Complete the task When review is clean or all open findings are adjudicated at the breaker cap, record completion in the ledger: - `Task <N>: complete (commits <base7>..<head7>, review clean)` - `Task <N>: complete (commits <base7>..<head7>, <K> parked)` Mark the todo complete and proceed to the next task. 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 The final whole-branch review gets a package too: run `python3 scripts/review-package.py PLAN_FILE MERGE_BASE HEAD` (MERGE_BASE = the commit the branch started from, e.g. `git merge-base main HEAD`) and include the printed path in the final review dispatch, so the final reviewer reads one file instead of re-deriving the branch diff with git commands. Dispatch using requesting-code-review's [code-reviewer.md](../requesting-code-review/code-reviewer.md). Point it at the ledger's deferred-minor and parked lines so it can triage which must be fixed before merge. If the final whole-branch review returns findings, dispatch ONE fix subagent with the complete findings list — not one fixer per finding. Per-finding fixers each rebuild context and re-run suites; a real session's final-review fix wave cost more than all its tasks combined. Then run exactly one scoped re-review of the fix wave (`python3 scripts/review-package.py PLAN_FILE FIX_BASE HEAD` over the fix range, [re-review-prompt.md](re-review-prompt.md)). Adjudicate any residual findings as in the task loop's breaker: park with rulings, or rule on the load-bearing ones and ledger what you decided. Only the four classes above stop you here. There is no second fix wave — residual load-bearing findings surface to your human partner when finishing-a-development-branch presents the options. ## Finish Before you delete anything, collect every ledger line containing `Ruling:` — preflight rulings, parked findings, breaker adjudications, all of them — into your final message under "Rulings I made", in the order you made them, each with what it costs if wrong. The list is exhaustive: if the ledger holds a ruling, the list holds it. That list is the only place the decisions you took on your human partner's behalf reach them — they read it and rework whatever you got wrong. A ruling that dies with the workspace was a decision made in secret. When the final whole-branch review is clean and its fixes are merged, delete this plan's workspace (`rm -rf <workspace>`) — the git history is the record now. Sibling directories belong to other plans; leave them alone. Use finishing-a-development-branch. ## Operational Mechanics & Examples Detailed execution workflows and deep operational references: - [Workflow Examples & Rationalizations](references/workflow-examples.md) — Concrete walkthroughs, common rationalizations, and mental patterns. - [Task Loop Mechanics](references/task-loop-mechanics.md) — Subagent dispatching details, status triages, diff packaging edge cases, and breaker protocols.