@selesai/code 0.9.5 → 0.9.8

package/dist/skills/ponytail-debt/SKILL.md

@@ -1,45 +1,45 @@
----
-name: ponytail-debt
-description: >
-  Harvest every `ponytail:` comment in the codebase into a debt ledger, so the
-  deliberate shortcuts and deferrals ponytail leaves behind get tracked instead
-  of rotting into "later means never". Use when the user says "ponytail debt",
-  "/ponytail-debt", "what did ponytail defer", "list the shortcuts", "ponytail
-  ledger", or "what did we mark to do later". One-shot report, changes nothing.
-disable-model-invocation: true
----
-
-Every deliberate ponytail shortcut is marked with a `ponytail:` comment naming
-its ceiling and upgrade path. This collects them into one ledger so a deferral
-can't quietly become permanent.
-
-## Scan
-
-Grep the repo for comment markers, skipping `node_modules`, `.git`, and build
-output:
-
-`grep -rnE '(#|//) ?ponytail:' .`  (add other comment prefixes if your stack uses them)
-
-Each hit is one ledger row. The comment prefix keeps prose that merely mentions
-the convention out of the ledger.
-
-## Output
-
-One row per marker, grouped by file:
-
-`<file>:<line>, <what was simplified>. ceiling: <the limit named>. upgrade: <the trigger to revisit>.`
-
-The convention is `ponytail: <ceiling>, <upgrade path>`, so pull the ceiling
-and the trigger straight from the comment. Want an owner per row too? add
-`git blame -L<line>,<line>`.
-
-Flag the rot risk: any `ponytail:` comment that names no upgrade path or
-trigger gets a `no-trigger` tag, those are the ones that silently rot.
-
-End with `<N> markers, <M> with no trigger.` Nothing found: `No ponytail: debt. Clean ledger.`
-
-## Boundaries
-
-Reads and reports only, changes nothing. To persist it, ask and it writes the
-ledger to a file (e.g. `PONYTAIL-DEBT.md`). One-shot. "stop ponytail-debt" or
-"normal mode" to revert.
+---
+name: ponytail-debt
+description: >
+  Harvest every `ponytail:` comment in the codebase into a debt ledger, so the
+  deliberate shortcuts and deferrals ponytail leaves behind get tracked instead
+  of rotting into "later means never". Use when the user says "ponytail debt",
+  "/ponytail-debt", "what did ponytail defer", "list the shortcuts", "ponytail
+  ledger", or "what did we mark to do later". One-shot report, changes nothing.
+disable-model-invocation: true
+---
+
+Every deliberate ponytail shortcut is marked with a `ponytail:` comment naming
+its ceiling and upgrade path. This collects them into one ledger so a deferral
+can't quietly become permanent.
+
+## Scan
+
+Grep the repo for comment markers, skipping `node_modules`, `.git`, and build
+output:
+
+`grep -rnE '(#|//) ?ponytail:' .`  (add other comment prefixes if your stack uses them)
+
+Each hit is one ledger row. The comment prefix keeps prose that merely mentions
+the convention out of the ledger.
+
+## Output
+
+One row per marker, grouped by file:
+
+`<file>:<line>, <what was simplified>. ceiling: <the limit named>. upgrade: <the trigger to revisit>.`
+
+The convention is `ponytail: <ceiling>, <upgrade path>`, so pull the ceiling
+and the trigger straight from the comment. Want an owner per row too? add
+`git blame -L<line>,<line>`.
+
+Flag the rot risk: any `ponytail:` comment that names no upgrade path or
+trigger gets a `no-trigger` tag, those are the ones that silently rot.
+
+End with `<N> markers, <M> with no trigger.` Nothing found: `No ponytail: debt. Clean ledger.`
+
+## Boundaries
+
+Reads and reports only, changes nothing. To persist it, ask and it writes the
+ledger to a file (e.g. `PONYTAIL-DEBT.md`). One-shot. "stop ponytail-debt" or
+"normal mode" to revert.

package/dist/skills/ponytail-gain/SKILL.md

@@ -1,51 +1,51 @@
----
-name: ponytail-gain
-description: >
-  Show ponytail's measured impact as a compact scoreboard: less code, less
-  cost, more speed, from the benchmark medians. One-shot display, not a
-  persistent mode, and not a per-repo number. Trigger: /ponytail-gain,
-  "ponytail gain", "what does ponytail save", "show ponytail impact",
-  "ponytail scoreboard".
-disable-model-invocation: true
----
-
-# Ponytail Gain
-
-Display this scoreboard when invoked. One-shot: do NOT change mode, write flag
-files, or persist anything.
-
-The figures are the published benchmark medians (5 everyday tasks: email
-validator, debounce, CSV sum, countdown timer, rate limiter; three models:
-Haiku, Sonnet, Opus). They are measured, not computed from the current repo.
-Source: `benchmarks/` and the README.
-
-## Scoreboard
-
-Render plain ASCII bars. The bar length shows the measured range; the label
-carries the exact figure:
-
-```
-  ponytail gain                     benchmark median · 5 tasks · 3 models
-
-  Lines of code   no-skill  ████████████████████  100%
-                  ponytail  ██▌·················    6–20%   ▼ 80–94%
-  Cost            no-skill  ████████████████████  100%
-                  ponytail  █████▌··············   23–53%  ▼ 47–77%
-  Speed           ponytail  ▸ 3–6× faster
-
-  This repo:  /ponytail-debt  (shortcuts you deferred)
-              /ponytail-audit (what's still cuttable)
-```
-
-## Honesty boundary
-
-These are benchmark medians, not this repo. NEVER print a per-repo savings
-number ("you saved X lines/tokens here"): the unbuilt version was never
-written, so there is no real baseline to subtract from in a live repo. The
-only real per-repo figures come from `/ponytail-debt` (a counted ledger), and
-this card points there instead of inventing one.
-
-## Boundaries
-
-One-shot display. Edits nothing, changes no mode.
-"stop ponytail" or "normal mode": revert.
+---
+name: ponytail-gain
+description: >
+  Show ponytail's measured impact as a compact scoreboard: less code, less
+  cost, more speed, from the benchmark medians. One-shot display, not a
+  persistent mode, and not a per-repo number. Trigger: /ponytail-gain,
+  "ponytail gain", "what does ponytail save", "show ponytail impact",
+  "ponytail scoreboard".
+disable-model-invocation: true
+---
+
+# Ponytail Gain
+
+Display this scoreboard when invoked. One-shot: do NOT change mode, write flag
+files, or persist anything.
+
+The figures are the published benchmark medians (5 everyday tasks: email
+validator, debounce, CSV sum, countdown timer, rate limiter; three models:
+Haiku, Sonnet, Opus). They are measured, not computed from the current repo.
+Source: `benchmarks/` and the README.
+
+## Scoreboard
+
+Render plain ASCII bars. The bar length shows the measured range; the label
+carries the exact figure:
+
+```
+  ponytail gain                     benchmark median · 5 tasks · 3 models
+
+  Lines of code   no-skill  ████████████████████  100%
+                  ponytail  ██▌·················    6–20%   ▼ 80–94%
+  Cost            no-skill  ████████████████████  100%
+                  ponytail  █████▌··············   23–53%  ▼ 47–77%
+  Speed           ponytail  ▸ 3–6× faster
+
+  This repo:  /ponytail-debt  (shortcuts you deferred)
+              /ponytail-audit (what's still cuttable)
+```
+
+## Honesty boundary
+
+These are benchmark medians, not this repo. NEVER print a per-repo savings
+number ("you saved X lines/tokens here"): the unbuilt version was never
+written, so there is no real baseline to subtract from in a live repo. The
+only real per-repo figures come from `/ponytail-debt` (a counted ledger), and
+this card points there instead of inventing one.
+
+## Boundaries
+
+One-shot display. Edits nothing, changes no mode.
+"stop ponytail" or "normal mode": revert.

package/dist/skills/ponytail-help/SKILL.md

@@ -1,70 +1,70 @@
----
-name: ponytail-help
-description: >
-  Quick-reference card for all ponytail modes, skills, and commands.
-  One-shot display, not a persistent mode. Trigger: /ponytail-help,
-  "ponytail help", "what ponytail commands", "how do I use ponytail".
-disable-model-invocation: true
----
-
-# Ponytail Help
-
-Display this reference card when invoked. One-shot, do NOT change mode,
-write flag files, or persist anything.
-
-## Levels
-
-| Level | Trigger | What change |
-|-------|---------|-------------|
-| **Lite** | `/ponytail lite` | Build what's asked, name the lazier alternative in one line. |
-| **Full** | `/ponytail` | The ladder enforced: YAGNI → stdlib → native → one line → minimum. Default. |
-| **Ultra** | `/ponytail ultra` | YAGNI extremist. Deletion before addition. Challenges requirements before building. |
-
-Level sticks until changed or session end.
-
-## Skills
-
-| Skill | Trigger | What it does |
-|-------|---------|--------------|
-| **ponytail** | `/ponytail` | Lazy mode itself. Simplest solution that works. |
-| **ponytail-review** | `/ponytail-review` | Over-engineering review: `L42: yagni: factory, one product. Inline.` |
-| **ponytail-gain** | `/ponytail-gain` | Measured-impact scoreboard: less code, less cost, more speed. |
-| **ponytail-help** | `/ponytail-help` | This card. |
-
-Codex uses `@ponytail`, `@ponytail-review`, and `@ponytail-help`; Claude Code
-and OpenCode use the slash-command forms above (OpenCode ships `/ponytail` and
-`/ponytail-review`).
-
-## Deactivate
-
-Say "stop ponytail" or "normal mode". Resume anytime with `/ponytail`.
-`/ponytail off` also works.
-
-## Configure Default Mode
-
-Default mode = `full`, auto-active every session. Change it:
-
-**Environment variable** (highest priority):
-```bash
-export PONYTAIL_DEFAULT_MODE=ultra
-```
-
-**Config file** (`~/.config/ponytail/config.json`, Windows: `%APPDATA%\ponytail\config.json`):
-```json
-{ "defaultMode": "lite" }
-```
-
-Set `"off"` to disable auto-activation on session start, activate manually
-with `/ponytail` when wanted.
-
-Resolution: env var > config file > `full`.
-
-## Update
-
-Enable auto-update once: open `/plugin`, go to Marketplaces, pick ponytail, Enable auto-update. Claude Code then pulls new versions at startup (run `/reload-plugins` when it prompts). Manual refresh: `/plugin marketplace update ponytail` then `/reload-plugins`.
-
-If `/plugin` is not recognized, your Claude Code is out of date. Update it (`npm install -g @anthropic-ai/claude-code@latest`, or `brew upgrade claude-code`) and restart. Other hosts use their own update flow.
-
-## More
-
-Full docs + examples: https://github.com/DietrichGebert/ponytail
+---
+name: ponytail-help
+description: >
+  Quick-reference card for all ponytail modes, skills, and commands.
+  One-shot display, not a persistent mode. Trigger: /ponytail-help,
+  "ponytail help", "what ponytail commands", "how do I use ponytail".
+disable-model-invocation: true
+---
+
+# Ponytail Help
+
+Display this reference card when invoked. One-shot, do NOT change mode,
+write flag files, or persist anything.
+
+## Levels
+
+| Level | Trigger | What change |
+|-------|---------|-------------|
+| **Lite** | `/ponytail lite` | Build what's asked, name the lazier alternative in one line. |
+| **Full** | `/ponytail` | The ladder enforced: YAGNI → stdlib → native → one line → minimum. Default. |
+| **Ultra** | `/ponytail ultra` | YAGNI extremist. Deletion before addition. Challenges requirements before building. |
+
+Level sticks until changed or session end.
+
+## Skills
+
+| Skill | Trigger | What it does |
+|-------|---------|--------------|
+| **ponytail** | `/ponytail` | Lazy mode itself. Simplest solution that works. |
+| **ponytail-review** | `/ponytail-review` | Over-engineering review: `L42: yagni: factory, one product. Inline.` |
+| **ponytail-gain** | `/ponytail-gain` | Measured-impact scoreboard: less code, less cost, more speed. |
+| **ponytail-help** | `/ponytail-help` | This card. |
+
+Codex uses `@ponytail`, `@ponytail-review`, and `@ponytail-help`; Claude Code
+and OpenCode use the slash-command forms above (OpenCode ships `/ponytail` and
+`/ponytail-review`).
+
+## Deactivate
+
+Say "stop ponytail" or "normal mode". Resume anytime with `/ponytail`.
+`/ponytail off` also works.
+
+## Configure Default Mode
+
+Default mode = `full`, auto-active every session. Change it:
+
+**Environment variable** (highest priority):
+```bash
+export PONYTAIL_DEFAULT_MODE=ultra
+```
+
+**Config file** (`~/.config/ponytail/config.json`, Windows: `%APPDATA%\ponytail\config.json`):
+```json
+{ "defaultMode": "lite" }
+```
+
+Set `"off"` to disable auto-activation on session start, activate manually
+with `/ponytail` when wanted.
+
+Resolution: env var > config file > `full`.
+
+## Update
+
+Enable auto-update once: open `/plugin`, go to Marketplaces, pick ponytail, Enable auto-update. Claude Code then pulls new versions at startup (run `/reload-plugins` when it prompts). Manual refresh: `/plugin marketplace update ponytail` then `/reload-plugins`.
+
+If `/plugin` is not recognized, your Claude Code is out of date. Update it (`npm install -g @anthropic-ai/claude-code@latest`, or `brew upgrade claude-code`) and restart. Other hosts use their own update flow.
+
+## More
+
+Full docs + examples: https://github.com/DietrichGebert/ponytail

package/dist/skills/ponytail-review/SKILL.md

@@ -1,58 +1,58 @@
----
-name: ponytail-review
-description: >
-  Code review focused exclusively on over-engineering. Finds what to delete:
-  reinvented standard library, unneeded dependencies, speculative abstractions,
-  dead flexibility. One line per finding: location, what to cut, what replaces
-  it. Use when the user says "review for over-engineering", "what can we
-  delete", "is this over-engineered", "simplify review", or invokes
-  /ponytail-review. Complements correctness-focused review, this one only
-  hunts complexity.
-disable-model-invocation: true
----
-
-Review diffs for unnecessary complexity. One line per finding: location, what
-to cut, what replaces it. The diff's best outcome is getting shorter.
-
-## Format
-
-`L<line>: <tag> <what>. <replacement>.`, or `<file>:L<line>: ...` for
-multi-file diffs.
-
-Tags:
-
-- `delete:` dead code, unused flexibility, speculative feature. Replacement: nothing.
-- `stdlib:` hand-rolled thing the standard library ships. Name the function.
-- `native:` dependency or code doing what the platform already does. Name the feature.
-- `yagni:` abstraction with one implementation, config nobody sets, layer with one caller.
-- `shrink:` same logic, fewer lines. Show the shorter form.
-
-## Examples
-
-❌ "This EmailValidator class might be more complex than necessary, have you
-considered whether all these validation rules are needed at this stage?"
-
-✅ `L12-38: stdlib: 27-line validator class. "@" in email, 1 line, real validation is the confirmation mail.`
-
-✅ `L4: native: moment.js imported for one format call. Intl.DateTimeFormat, 0 deps.`
-
-✅ `repo.py:L88: yagni: AbstractRepository with one implementation. Inline it until a second one exists.`
-
-✅ `L52-71: delete: retry wrapper around an idempotent local call. Nothing replaces it.`
-
-✅ `L30-44: shrink: manual loop builds dict. dict(zip(keys, values)), 1 line.`
-
-## Scoring
-
-End with the only metric that matters: `net: -<N> lines possible.`
-
-If there is nothing to cut, say `Lean already. Ship.` and stop.
-
-## Boundaries
-
-Scope: over-engineering and complexity only. Correctness bugs, security holes,
-and performance are explicitly out of scope. Route them to a normal review
-pass, not this one. A single smoke test or `assert`-based
-self-check is the ponytail minimum, not bloat, never flag it for deletion.
-Does not apply the fixes, only lists them.
-"stop ponytail-review" or "normal mode": revert to verbose review style.
+---
+name: ponytail-review
+description: >
+  Code review focused exclusively on over-engineering. Finds what to delete:
+  reinvented standard library, unneeded dependencies, speculative abstractions,
+  dead flexibility. One line per finding: location, what to cut, what replaces
+  it. Use when the user says "review for over-engineering", "what can we
+  delete", "is this over-engineered", "simplify review", or invokes
+  /ponytail-review. Complements correctness-focused review, this one only
+  hunts complexity.
+disable-model-invocation: true
+---
+
+Review diffs for unnecessary complexity. One line per finding: location, what
+to cut, what replaces it. The diff's best outcome is getting shorter.
+
+## Format
+
+`L<line>: <tag> <what>. <replacement>.`, or `<file>:L<line>: ...` for
+multi-file diffs.
+
+Tags:
+
+- `delete:` dead code, unused flexibility, speculative feature. Replacement: nothing.
+- `stdlib:` hand-rolled thing the standard library ships. Name the function.
+- `native:` dependency or code doing what the platform already does. Name the feature.
+- `yagni:` abstraction with one implementation, config nobody sets, layer with one caller.
+- `shrink:` same logic, fewer lines. Show the shorter form.
+
+## Examples
+
+❌ "This EmailValidator class might be more complex than necessary, have you
+considered whether all these validation rules are needed at this stage?"
+
+✅ `L12-38: stdlib: 27-line validator class. "@" in email, 1 line, real validation is the confirmation mail.`
+
+✅ `L4: native: moment.js imported for one format call. Intl.DateTimeFormat, 0 deps.`
+
+✅ `repo.py:L88: yagni: AbstractRepository with one implementation. Inline it until a second one exists.`
+
+✅ `L52-71: delete: retry wrapper around an idempotent local call. Nothing replaces it.`
+
+✅ `L30-44: shrink: manual loop builds dict. dict(zip(keys, values)), 1 line.`
+
+## Scoring
+
+End with the only metric that matters: `net: -<N> lines possible.`
+
+If there is nothing to cut, say `Lean already. Ship.` and stop.
+
+## Boundaries
+
+Scope: over-engineering and complexity only. Correctness bugs, security holes,
+and performance are explicitly out of scope. Route them to a normal review
+pass, not this one. A single smoke test or `assert`-based
+self-check is the ponytail minimum, not bloat, never flag it for deletion.
+Does not apply the fixes, only lists them.
+"stop ponytail-review" or "normal mode": revert to verbose review style.

package/dist/skills/selesai-handoff/SKILL.md

@@ -1,20 +1,20 @@
----
-name: selesai-handoff
-description: Hand the current conversation off to a fresh background agent that picks up the work immediately.
-argument-hint: "What will the next session be used for?"
-disable-model-invocation: true
----
-
-Write a handoff summary of the current conversation so a fresh agent can continue the work. Instead of saving it, launch a background agent seeded with the summary as its prompt: `selesai --name "<descriptive name>" -p "<handoff summary>"`. It starts in the current working directory and returns immediately; the user manages it with `selesai agents`.
-
-Always pass `-n`/`--name` with a descriptive name (e.g. `--name "Fix login bug"`) — it sets the display name shown in the job list, session picker, and terminal title.
-
-You might want to use something like `nohup` or `Start-Process` or `start /b` or etc. before the selesai command to spawn background command.
-
-Include a "suggested skills" section in the summary, which suggests skills that the agent should invoke.
-
-Do not duplicate content already captured in other artifacts (PRDs, plans, ADRs, issues, commits, diffs). Reference them by path or URL instead.
-
-Redact any sensitive information, such as API keys, passwords, or personally identifiable information — the summary becomes the agent's prompt.
-
-If the user passed arguments, treat them as a description of what the next session will focus on and tailor the summary accordingly.
+---
+name: selesai-handoff
+description: Hand the current conversation off to a fresh background agent that picks up the work immediately.
+argument-hint: "What will the next session be used for?"
+disable-model-invocation: true
+---
+
+Write a handoff summary of the current conversation so a fresh agent can continue the work. Instead of saving it, launch a background agent seeded with the summary as its prompt: `selesai --name "<descriptive name>" -p "<handoff summary>"`. It starts in the current working directory and returns immediately; the user manages it with `selesai agents`.
+
+Always pass `-n`/`--name` with a descriptive name (e.g. `--name "Fix login bug"`) — it sets the display name shown in the job list, session picker, and terminal title.
+
+You might want to use something like `nohup` or `Start-Process` or `start /b` or etc. before the selesai command to spawn background command.
+
+Include a "suggested skills" section in the summary, which suggests skills that the agent should invoke.
+
+Do not duplicate content already captured in other artifacts (PRDs, plans, ADRs, issues, commits, diffs). Reference them by path or URL instead.
+
+Redact any sensitive information, such as API keys, passwords, or personally identifiable information — the summary becomes the agent's prompt.
+
+If the user passed arguments, treat them as a description of what the next session will focus on and tailor the summary accordingly.

package/dist/skills/workflow-creation/SKILL.md

@@ -1,73 +1,73 @@
----
-name: workflow-creation
-description: Creates durable Selesai workflow modes. Use when a user asks to create or change a workflow mode, phased agent flow, or slash-command workflow.
-disable-model-invocation: true
----
-
-# Durable Workflows
-
-**Durable** means `workflow.json`, not session history, is the run authority. Build on the shared engine in `src/extensions/workflow/`; a mode is configuration, not a second orchestrator.
-
-## 1. Choose the smallest fit
-
-Read `docs/workflows.md`, every file in `src/extensions/workflow/modes/`, and the relevant workflow tests.
-
-- Reuse `prototype`, `quick`, or `task` when its phase graph and terminal gate fit; change only its prompts/configuration.
-- Add a mode only for a materially different graph, artifact contract, or close gate.
-
-Done when the request is mapped to one existing mode or a named new mode with its phase list and terminal artifact.
-
-## 2. Trace the durable seam
-
-Before changing engine-facing behavior, read completely:
-
-- `state-machine.ts` — graph, artifact gates, terminal-ready, completion;
-- `adapter.ts` — tools, event handlers, persistence, reload guards;
-- `run-state.ts` — canonical record and resume validation;
-- `extension.ts` — single extension mounting all modes.
-
-Done when every proposed behavior has one owner: state machine, shared adapter, or mode configuration.
-
-## 3. Implement the mode
-
-For a new mode, add `src/extensions/workflow/modes/<name>.ts`, modeled on `quick.ts`, with only `WorkflowConfig` and `WorkflowModeRegistration`:
-
-- ordered phases, phase artifacts, prompts, validators, close artifacts/validators;
-- unique mode/status/entry identities and slash-command name; users start/resume through that command, while the shared end tool selects the mode;
-- prompts that name exact artifact paths and use `write_workflow_artifact` only for workflow artifacts.
-
-Register the mode once in `MODES` in `extension.ts`; document its lifecycle and commands in `docs/workflows.md`.
-
-Done when the mode file has no filesystem, persistence, event-registration, or controller code.
-
-## 4. Preserve the durable contract
-
-The shared adapter owns UUID artifact directories, atomic saves, resume, loop review state, and reload safety. Do not reimplement them per mode.
-
-- Persisted state changes after start, artifact/loop transition, resume reconciliation, and explicit end.
-- Never auto-resume on `session_start`; only a user-invoked mode command with an explicit selector attaches a run.
-- Artifact completion advances durable state then stops the parent turn; the user deliberately continues the attached mode.
-- Terminal-ready stays active. Only `end_workflow({ mode })` marks the record completed and terminates.
-- One `ExtensionAPI` hosts all modes: shared writer once, stale reload handlers inert, one attached run total.
-- Builder/reviewer loops use adapter-owned rounds, review files, markers, and max-iteration pause.
-
-Done when the new behavior preserves every applicable invariant above.
-
-## 5. Lock the mode with real seams
-
-Extend the existing fake-Pi tests; do not add another framework. Cover the real mode, not only state-machine units:
-
-- start writes valid `workflow.json`; artifact transition updates it; explicit end completes it;
-- explicit resume reconciles an artifact written before a phase save;
-- loop round/review path resumes when the mode has a loop;
-- terminal-ready does not complete early;
-- extension reload ignores stale handlers; inactive sibling modes do not react.
-
-Run the narrow mode test, then:
-
-```bash
-npx vitest run src/__tests__/state-machine.test.ts src/__tests__/adapter.test.ts src/__tests__/workflow-race.test.ts src/__tests__/workflow-run-state.test.ts src/__tests__/<mode>-workflow.test.ts
-npm run build
-```
-
-Done when those checks pass and the diff contains only the selected mode, shared-engine changes proven necessary by a failing regression, documentation, and tests.
+---
+name: workflow-creation
+description: Creates durable Selesai workflow modes. Use when a user asks to create or change a workflow mode, phased agent flow, or slash-command workflow.
+disable-model-invocation: true
+---
+
+# Durable Workflows
+
+**Durable** means `workflow.json`, not session history, is the run authority. Build on the shared engine in `src/extensions/workflow/`; a mode is configuration, not a second orchestrator.
+
+## 1. Choose the smallest fit
+
+Read `docs/workflows.md`, every file in `src/extensions/workflow/modes/`, and the relevant workflow tests.
+
+- Reuse `prototype`, `quick`, or `task` when its phase graph and terminal gate fit; change only its prompts/configuration.
+- Add a mode only for a materially different graph, artifact contract, or close gate.
+
+Done when the request is mapped to one existing mode or a named new mode with its phase list and terminal artifact.
+
+## 2. Trace the durable seam
+
+Before changing engine-facing behavior, read completely:
+
+- `state-machine.ts` — graph, artifact gates, terminal-ready, completion;
+- `adapter.ts` — tools, event handlers, persistence, reload guards;
+- `run-state.ts` — canonical record and resume validation;
+- `extension.ts` — single extension mounting all modes.
+
+Done when every proposed behavior has one owner: state machine, shared adapter, or mode configuration.
+
+## 3. Implement the mode
+
+For a new mode, add `src/extensions/workflow/modes/<name>.ts`, modeled on `quick.ts`, with only `WorkflowConfig` and `WorkflowModeRegistration`:
+
+- ordered phases, phase artifacts, prompts, validators, close artifacts/validators;
+- unique mode/status/entry identities and slash-command name; users start/resume through that command, while the shared end tool selects the mode;
+- prompts that name exact artifact paths and use `write_workflow_artifact` only for workflow artifacts.
+
+Register the mode once in `MODES` in `extension.ts`; document its lifecycle and commands in `docs/workflows.md`.
+
+Done when the mode file has no filesystem, persistence, event-registration, or controller code.
+
+## 4. Preserve the durable contract
+
+The shared adapter owns UUID artifact directories, atomic saves, resume, loop review state, and reload safety. Do not reimplement them per mode.
+
+- Persisted state changes after start, artifact/loop transition, resume reconciliation, and explicit end.
+- Never auto-resume on `session_start`; only a user-invoked mode command with an explicit selector attaches a run.
+- Artifact completion advances durable state then stops the parent turn; the user deliberately continues the attached mode.
+- Terminal-ready stays active. Only `end_workflow({ mode })` marks the record completed and terminates.
+- One `ExtensionAPI` hosts all modes: shared writer once, stale reload handlers inert, one attached run total.
+- Builder/reviewer loops use adapter-owned rounds, review files, markers, and max-iteration pause.
+
+Done when the new behavior preserves every applicable invariant above.
+
+## 5. Lock the mode with real seams
+
+Extend the existing fake-Pi tests; do not add another framework. Cover the real mode, not only state-machine units:
+
+- start writes valid `workflow.json`; artifact transition updates it; explicit end completes it;
+- explicit resume reconciles an artifact written before a phase save;
+- loop round/review path resumes when the mode has a loop;
+- terminal-ready does not complete early;
+- extension reload ignores stale handlers; inactive sibling modes do not react.
+
+Run the narrow mode test, then:
+
+```bash
+npx vitest run src/__tests__/state-machine.test.ts src/__tests__/adapter.test.ts src/__tests__/workflow-race.test.ts src/__tests__/workflow-run-state.test.ts src/__tests__/<mode>-workflow.test.ts
+npm run build
+```
+
+Done when those checks pass and the diff contains only the selected mode, shared-engine changes proven necessary by a failing regression, documentation, and tests.