@milehimikey/em 1.14.2 → 1.16.0

package/dist/templates.d.ts

@@ -5,7 +5,7 @@ export declare const MODEL_README_TEMPLATE = "# {{Model Name}}\n\n{{One-paragrap
 export declare const STATE_TEMPLATE = "<!--\nResumable progress state for an event model. Stored as <model>/.event-modeling.md\nThe skill reads this on `/event-modeling` (no arg) to resume where you left off.\nKeep it current at the end of every working session.\n-->\n\n# Event Modeling Progress \u2014 {{Model Name}}\n\n- **Model file:** `{{model-name}}.em`\n- **Em version:** {{X.Y.Z}}\n- **Current phase:** {{discover | extract | model | slice | implement | conform | review | validate}}\n- **Current step:** {{1\u20137, see methodology; or extraction round R1\u2013R7}}\n- **Last updated:** {{YYYY-MM-DD}}\n- **Last conformance:** {{YYYY-MM-DD @ <target-repo revision> \u2014 report: conformance/<date>-report.md | never}}\n- **Model version:** {{N | none}}\n- **Certified:** {{v<N> @ <target-repo revision> (YYYY-MM-DD) | never}}\n- **Last stakeholder review:** {{YYYY-MM-DD \u2014 attendees: see Participants | never}}\n\n## Session inputs\n- **Scope line:** {{one-line description of what's in/out of bounds for this model}}\n- **PRD / spec reference:** {{path, link, or \"none\"}}\n- **Headless/API model:** {{yes | no}}\n- **Source mode:** {{greenfield | extract-event-driven | extract-procedural}}\n- **Existing system refs:** {{repo paths, event-schema/topic locations, docs \u2014 or \"n/a\"}}\n\n## Participants\n<!-- Populate at session start. Live workshop: one human proxy relays questions to the room;\n     attribute every answer/decision in the Decisions log to a named participant here. -->\n- {{Name}} \u2014 {{role}} \u2014 {{domain area}}\n\n## Extraction progress (existing-system models only \u2014 delete for greenfield)\n- [ ] R1. Candidate events (extracted/synthesized, filtered, confirmed)\n- [ ] R2. Timeline order (as-is narrative, actors/callers, first render)\n- [ ] R3. Commands / inputs\n- [ ] R4. Read models / outputs (validate from here)\n- [ ] R5. Boundaries & reactions (reaction shares its slice with the command it triggers)\n- [ ] R6. Gap & TBD reconciliation\n- [ ] R7. Convergence (render + validate clean, user confirmed as-is)\n\n## Steps completed\n- [ ] 1. Brainstorm events\n- [ ] 2. Plot / storyboard (personas + UI)\n- [ ] 3. Inputs (commands)\n- [ ] 4. Outputs (read models)\n- [ ] 5. Swimlanes & apply patterns\n- [ ] 6. Elaborate scenarios\n- [ ] 7. Evaluate completeness (`em validate` clean)\n\n## Decisions log\n<!-- Resolved choices, with the reasoning, so they aren't re-litigated. In a live workshop,\n     attribute each entry to the participant who made the call (see Participants above).\n     Every entry is a dated bullet (\"- YYYY-MM-DD: ...\"); em changelog skips any other line.\n     Seam change request (a needed change to another model's public element; never edit that\n     model, keep the open question blocked on its owners):\n     - YYYY-MM-DD: seam change request \u2192 <producerKey>:<kind>.<slug> \u2014 <what> \u2014 <why> -->\n- {{YYYY-MM-DD}}: {{decision}} \u2014 {{why}} \u2014 by {{participant, if a live workshop}}\n\n## Usage log\n<!-- The team's only usage signal today (see docs/usage-data.md) \u2014 cheap and coarse on purpose.\n     One line per session: phase(s) touched, and validate diagnostic *categories* hit (one of\n     the exact fixed strings in docs/usage-data.md#categories, e.g. \"read model has no\n     consumer\" \u2014 never the full instance message or any domain content). Append, never edit\n     past entries. -->\n- {{YYYY-MM-DD}}: phases: {{discover | extract | model | slice | implement | conform | review | validate | watch, ...}} \u2014 validate: {{diagnostic category (docs/usage-data.md#categories), ... | none}}\n\n## Open questions / parking lot\n<!-- Unresolved items to bring back to the user. Never guess these. Metadata is optional and\n     flat \u2014 add only what's known: source (ticket/conversation that spawned it), blocked on\n     (who/what), revisit (when). -->\n- [ ] {{question}} \u2014 source: {{ticket/conversation link, optional}} \u2014 blocked on: {{who/what, optional}} \u2014 revisit: {{when, optional}}\n\n## Slice inventory\n<!-- Deliberately NOT a table: the canonical slice index (slice, pattern, status, doc link)\n     lives in README.md's \"Slices\" section \u2014 one source of truth, updated there. This file\n     only tracks resumable session state. -->\nSee `README.md` \u2192 **Slices** for the slice index and per-slice doc status.\n";
 /** Raw copy of templates/constitution.md, \`{{...}}\` placeholders intact — see
  *  scaffoldConstitution(). */
-export declare const CONSTITUTION_TEMPLATE = "<!--\nThe implementation constitution: the house rules an implementing agent follows on EVERY slice \u2014\nstack, code style, testing norms, NFR baselines, review norms. It answers \"how do we build things\nhere\" once, so no slice doc has to repeat it and no agent has to invent it. Slice docs say WHAT to\nbuild; this says HOW it gets built here.\n\nWhere this document lives:\n  - No SDD tool: `constitution.md` beside the model \u2014 `em scaffold` writes it there.\n  - spec-kit project (a `.specify/` directory exists anywhere above the model): the document IS\n    `.specify/memory/constitution.md`. em writes no second copy; the sections below merge into\n    that file under these same headings, never overwriting text already there, and ratification is\n    recorded in spec-kit's own `**Ratified**:` footer line instead of the frontmatter below.\n\nHow it gets filled: not by an agent guessing. Each section opens with the question a short\nfacilitated conversation asks before the first slice is implemented \u2014 the procedure is \"Before the\nfirst slice: the constitution\" in the `event-modeling-implement` skill's `reference/implement.md`\n(`em contract` prints it). Replace each `{{...}}` block with the real answers; delete the guidance\ncomments and any row that doesn't apply.\n\nRatification: `ratifiedBy:`/`ratifiedOn:` are the same identity discipline slice docs use \u2014 a\nNAMED human and an ISO date, hand-filled at sign-off (no `em` command writes this file).\n**A constitution with an empty `ratifiedBy:` is a draft**: an implementing agent treats it as\nunratified, says so, and does not proceed on unilateral style or stack decisions for a first slice.\n\n`em status` reports this document as present or absent per model \u2014 existence only. em never reads\nor validates its content, and the CLI parses nothing here. Three lines are read as plain text by\nthe engagement skill and its sub-agents, so keep their exact shape: `- **Test command:**` (the\nvalidator), `- **Merge strategy:**` and `- **Agent models:**` (the engagement skill). In a spec-kit\nproject they merge under the same headings in `.specify/memory/constitution.md`.\n-->\n\n---\nschemaVersion: 1\nratifiedBy:\nratifiedOn:\n---\n# {{Project Name}} \u2014 implementation constitution\n\nThe house rules for how implementation happens in this project. They bound every \"purely\ntechnical choice\" an implementing agent would otherwise make alone.\n\n## Stack and architectural shape\n\n> **What do we build on, what shape does the code take, and which implementation skill or\n> approach does each slice pattern route to?**\n\n- **Languages / runtimes:** {{e.g. Kotlin 2.x on JVM 21; TypeScript 5 on Node 24}}\n- **Frameworks / platform:** {{web framework, persistence, messaging, build tool}}\n- **Architectural pattern:** {{e.g. event-sourced CQRS with vertical slices; layered service over\n  a relational store; functional core / imperative shell}}\n- **Where a slice's code lives:** {{one package per slice, per context, ...}}\n- **Interface conventions:** {{resource style \u2014 REST/RPC/GraphQL, etc.; error/rejection mapping;\n  versioning; auth at the edge \u2014 the shape every `ui`-triggered command or `ui`-consumed view's\n  endpoint follows, decided once here rather than invented per slice}}\n\nRouting \u2014 which implementation skill or approach each of the four slice patterns uses:\n\n| Pattern | Skill / approach |\n|---|---|\n| State Change | {{e.g. the `axon-*` skill set \u2014 axon-entity-patterns, then axon-entity-testing}} |\n| State View | {{e.g. the `axon-*` skill set \u2014 axon-projection-patterns, then axon-projection-testing}} |\n| Automation | {{e.g. the `axon-*` skill set \u2014 axon-policy-patterns, then axon-policy-testing}} |\n| Translation | {{e.g. the `axon-*` skill set \u2014 axon-translation-patterns}} |\n\nAn agent implementing a slice reads the doc's `pattern:` frontmatter and follows that row \u2014 this\ntable is the only routing rule.\n\n## Code style\n\n> **What does \"idiomatic\" mean in this codebase \u2014 formatting, naming, module layout?**\n\n- **Formatter / linter:** {{the tool and the command that runs it \u2014 never hand-format against it}}\n- **Naming:** {{commands, events, handlers, files, test names}}\n- **Module layout:** {{what lives in which file/package, and what may not import what}}\n- **Idiomatic here means:** {{the two or three habits a new contributor most often gets wrong}}\n\n## Testing norms\n\n> **What must be tested for each slice pattern, where do those tests live, and how are they named\n> so `em coverage` can trace invariant IDs?**\n\n- **Levels required per pattern:** {{e.g. State Change \u2014 decider unit tests plus a\n  given/when/then fixture test; State View \u2014 projection tests; Automation / Translation \u2014\n  reaction tests, including a negative case}}\n- **Invariant tests:** {{where they live}} \u2014 every `INV-<MNEMONIC>-n` in a slice doc needs at least\n  one test **citing that exact ID** in its name or a comment, so\n  `em coverage <model>.em --tests <dir>` can trace it.\n- **Scenario tests:** {{where they live}} \u2014 one per `## Scenarios (Given / When / Then)` entry,\n  with rejection scenarios asserting the doc's named rejection reason.\n- **Test naming convention:** {{the exact pattern, e.g. `INV-ORD-3: rejects a second submit`}}\n- **What \"green\" means:** {{the command CI runs}}\n- **Test command:** `{{the one command that runs the tests, e.g. ./gradlew test}}`\n  What the `em-validator` sub-agent runs. Keep exactly this shape: one line, the command in\n  backticks. Absent, the validator reports \"no test command in the constitution\" and runs only the\n  em checks.\n\n## NFR baselines\n\n> **What standing non-functional defaults does every slice inherit \u2014 authz, PII, performance,\n> observability?**\n\n- **Authorization model:** {{who may issue which commands, how it's enforced, and where}}\n- **PII / data handling:** {{what is sensitive, what may be logged, retention}}\n- **Performance defaults:** {{latency / throughput budgets that apply unless a slice says otherwise}}\n- **Observability:** {{logging, metrics, tracing every slice is expected to emit}}\n\nA slice doc's own `## Non-Functional Requirements` section overrides these for that slice; where\nit is silent, these apply.\n\n## Review and merge norms\n\n> **Who reviews an implementation PR, what blocks a merge, and how does the slice doc's status\n> flip fit in?**\n\n- **Reviewers:** {{who \u2014 a team, a CODEOWNERS rule, the slice's ratifier}}\n- **What blocks a merge:** {{e.g. a failing suite, an uncovered invariant, a gap that belongs back\n  at the model}}\n- **Branch / commit conventions:** {{...}} \u2014 name only branch naming and commit-message style\n  here. **One slice doc = one PR is the implement contract's rule, not this document's to\n  amend** \u2014 a `covers:` doc ships as one PR for both keys; a read model is one doc, so a later\n  `again` instance is a continuation of the doc that first declared it, not a PR of its own. See\n  the agent guide's \u00A75/\u00A710.\n- **Merge strategy:** merge-commits-when-stacked\n  {{**How do PRs merge, and what happens when one PR depends on another?** Merge commits whenever\n  a dependent PR is open; squash only a PR with no open dependent (implement contract \u00A78 rule 2a).\n  Keep this exact line: it is the only value the engagement skill accepts, and it refuses to run\n  without it.}}\n- **Agent models:** implementer=sonnet, validator=sonnet, reviewer=sonnet, critic=opus\n  {{**Which model runs each em sub-agent?** Keep this exact line shape, with the defaults shown or\n  your own choices. The critic must run on a different model from the implementer; `critic=codex`\n  selects the Codex critic. Absent, the engagement skill states these defaults once and\n  proceeds.}}\n- **At merge:** run `em slice mark-implemented <model>.em <slice-key> <pr-url>` \u2014 the one edit an\n  implementing agent makes to a ratified slice doc, run by {{the PR author | CI}}. Never bump\n  `version:`; that moves only when a delta is ratified.\n";
+export declare const CONSTITUTION_TEMPLATE = "<!--\nThe implementation constitution: the house rules an implementing agent follows on EVERY slice \u2014\nstack, code style, testing norms, NFR baselines, review norms. It answers \"how do we build things\nhere\" once, so no slice doc has to repeat it and no agent has to invent it. Slice docs say WHAT to\nbuild; this says HOW it gets built here.\n\nWhere this document lives:\n  - No SDD tool: `constitution.md` beside the model \u2014 `em scaffold` writes it there.\n  - spec-kit project (a `.specify/` directory exists anywhere above the model): the document IS\n    `.specify/memory/constitution.md`. em writes no second copy; the sections below merge into\n    that file under these same headings, never overwriting text already there, and ratification is\n    recorded in spec-kit's own `**Ratified**:` footer line instead of the frontmatter below.\n\nHow it gets filled: not by an agent guessing. Each section opens with the question a short\nfacilitated conversation asks before the first slice is implemented \u2014 the procedure is \"Before the\nfirst slice: the constitution\" in the `event-modeling-implement` skill's `reference/implement.md`\n(`em contract` prints it). Replace each `{{...}}` block with the real answers; delete the guidance\ncomments and any row that doesn't apply.\n\nRatification: `ratifiedBy:`/`ratifiedOn:` are the same identity discipline slice docs use \u2014 a\nNAMED human and an ISO date, hand-filled at sign-off (no `em` command writes this file).\n**A constitution with an empty `ratifiedBy:` is a draft**: an implementing agent treats it as\nunratified, says so, and does not proceed on unilateral style or stack decisions for a first slice.\n\n`em status` reports this document as present or absent per model \u2014 existence only. em never reads\nor validates its content, and the CLI parses nothing here. Two lines are read as plain text by\nthe engagement skill and its sub-agents, so keep their exact shape: `- **Test command:**` (the\nvalidator) and `- **Agent models:**` (the engagement skill). In a spec-kit\nproject they merge under the same headings in `.specify/memory/constitution.md`.\n-->\n\n---\nschemaVersion: 1\nratifiedBy:\nratifiedOn:\n---\n# {{Project Name}} \u2014 implementation constitution\n\nThe house rules for how implementation happens in this project. They bound every \"purely\ntechnical choice\" an implementing agent would otherwise make alone.\n\n## Stack and architectural shape\n\n> **What do we build on, what shape does the code take, and which implementation skill or\n> approach does each slice pattern route to?**\n\n- **Languages / runtimes:** {{e.g. Kotlin 2.x on JVM 21; TypeScript 5 on Node 24}}\n- **Frameworks / platform:** {{web framework, persistence, messaging, build tool}}\n- **Architectural pattern:** {{e.g. event-sourced CQRS with vertical slices; layered service over\n  a relational store; functional core / imperative shell}}\n- **Where a slice's code lives:** {{one package per slice, per context, ...}}\n- **Interface conventions:** {{resource style \u2014 REST/RPC/GraphQL, etc.; error/rejection mapping;\n  versioning; auth at the edge \u2014 the shape every `ui`-triggered command or `ui`-consumed view's\n  endpoint follows, decided once here rather than invented per slice}}\n\nRouting \u2014 which implementation skill or approach each of the four slice patterns uses:\n\n| Pattern | Skill / approach |\n|---|---|\n| State Change | {{e.g. the `axon-*` skill set \u2014 axon-entity-patterns, then axon-entity-testing}} |\n| State View | {{e.g. the `axon-*` skill set \u2014 axon-projection-patterns, then axon-projection-testing}} |\n| Automation | {{e.g. the `axon-*` skill set \u2014 axon-policy-patterns, then axon-policy-testing}} |\n| Translation | {{e.g. the `axon-*` skill set \u2014 axon-translation-patterns}} |\n\nAn agent implementing a slice reads the doc's `pattern:` frontmatter and follows that row \u2014 this\ntable is the only routing rule.\n\n## Code style\n\n> **What does \"idiomatic\" mean in this codebase \u2014 formatting, naming, module layout?**\n\n- **Formatter / linter:** {{the tool and the command that runs it \u2014 never hand-format against it}}\n- **Naming:** {{commands, events, handlers, files, test names}}\n- **Module layout:** {{what lives in which file/package, and what may not import what}}\n- **Idiomatic here means:** {{the two or three habits a new contributor most often gets wrong}}\n\n## Testing norms\n\n> **What must be tested for each slice pattern, where do those tests live, and how are they named\n> so `em coverage` can trace invariant IDs?**\n\n- **Levels required per pattern:** {{e.g. State Change \u2014 decider unit tests plus a\n  given/when/then fixture test; State View \u2014 projection tests; Automation / Translation \u2014\n  reaction tests, including a negative case}}\n- **Invariant tests:** {{where they live}} \u2014 every `INV-<MNEMONIC>-n` in a slice doc needs at least\n  one test **citing that exact ID** in its name or a comment, so\n  `em coverage <model>.em --tests <dir>` can trace it.\n- **Scenario tests:** {{where they live}} \u2014 one per `## Scenarios (Given / When / Then)` entry,\n  with rejection scenarios asserting the doc's named rejection reason.\n- **Test naming convention:** {{the exact pattern, e.g. `INV-ORD-3: rejects a second submit`}}\n- **What \"green\" means:** {{the command CI runs}}\n- **Test command:** `{{the one command that runs the tests, e.g. ./gradlew test}}`\n  What the `em-validator` sub-agent runs. Keep exactly this shape: one line, the command in\n  backticks. Absent, the validator reports \"no test command in the constitution\" and runs only the\n  em checks.\n\n## NFR baselines\n\n> **What standing non-functional defaults does every slice inherit \u2014 authz, PII, performance,\n> observability?**\n\n- **Authorization model:** {{who may issue which commands, how it's enforced, and where}}\n- **PII / data handling:** {{what is sensitive, what may be logged, retention}}\n- **Performance defaults:** {{latency / throughput budgets that apply unless a slice says otherwise}}\n- **Observability:** {{logging, metrics, tracing every slice is expected to emit}}\n\nA slice doc's own `## Non-Functional Requirements` section overrides these for that slice; where\nit is silent, these apply.\n\n## Review and merge norms\n\n> **Who reviews an implementation PR, what blocks a merge, and how does the slice doc's status\n> flip fit in?**\n\n- **Reviewers:** {{who \u2014 a team, a CODEOWNERS rule, the slice's ratifier}}\n- **What blocks a merge:** {{e.g. a failing suite, an uncovered invariant, a gap that belongs back\n  at the model}}\n- **Branch / commit conventions:** {{...}} \u2014 name only branch naming and commit-message style\n  here. **One slice doc = one PR is the implement contract's rule, not this document's to\n  amend** \u2014 a `covers:` doc ships as one PR for both keys; a read model is one doc, so a later\n  `again` instance is a continuation of the doc that first declared it, not a PR of its own. See\n  the agent guide's \u00A75/\u00A710.\n- **Merge strategy:** {{squash | merge commit | rebase \u2014 the project's own choice. Every slice PR\n  is cut from and targets `main` (implement contract \u00A78 rule 2), so no PR ever depends on\n  another and any strategy works; em reads nothing from this line.}}\n- **Agent models:** implementer=sonnet, validator=sonnet, reviewer=sonnet, critic=opus\n  {{**Which model runs each em sub-agent?** Keep this exact line shape, with the defaults shown or\n  your own choices. The critic must run on a different model from the implementer; `critic=codex`\n  selects the Codex critic. Absent, the engagement skill states these defaults once and\n  proceeds.}}\n- **At merge:** run `em slice mark-implemented <model>.em <slice-key> <pr-url>` \u2014 the one edit an\n  implementing agent makes to a ratified slice doc, run by {{the PR author | CI}}. Never bump\n  `version:`; that moves only when a delta is ratified.\n";
 /** Same STARTER_EM content `em init` writes, titled from an arbitrary display name — used by
  *  `em scaffold`, which (unlike `em init`) knows a name to title the model with. */
 export declare function starterEmFor(title: string): string;

package/dist/templates.js

@@ -211,9 +211,9 @@ NAMED human and an ISO date, hand-filled at sign-off (no \`em\` command writes t
 unratified, says so, and does not proceed on unilateral style or stack decisions for a first slice.
 
 \`em status\` reports this document as present or absent per model — existence only. em never reads
-or validates its content, and the CLI parses nothing here. Three lines are read as plain text by
+or validates its content, and the CLI parses nothing here. Two lines are read as plain text by
 the engagement skill and its sub-agents, so keep their exact shape: \`- **Test command:**\` (the
-validator), \`- **Merge strategy:**\` and \`- **Agent models:**\` (the engagement skill). In a spec-kit
+validator) and \`- **Agent models:**\` (the engagement skill). In a spec-kit
 project they merge under the same headings in \`.specify/memory/constitution.md\`.
 -->
 
@@ -308,11 +308,9 @@ it is silent, these apply.
   amend** — a \`covers:\` doc ships as one PR for both keys; a read model is one doc, so a later
   \`again\` instance is a continuation of the doc that first declared it, not a PR of its own. See
   the agent guide's §5/§10.
-- **Merge strategy:** merge-commits-when-stacked
-  {{**How do PRs merge, and what happens when one PR depends on another?** Merge commits whenever
-  a dependent PR is open; squash only a PR with no open dependent (implement contract §8 rule 2a).
-  Keep this exact line: it is the only value the engagement skill accepts, and it refuses to run
-  without it.}}
+- **Merge strategy:** {{squash | merge commit | rebase — the project's own choice. Every slice PR
+  is cut from and targets \`main\` (implement contract §8 rule 2), so no PR ever depends on
+  another and any strategy works; em reads nothing from this line.}}
 - **Agent models:** implementer=sonnet, validator=sonnet, reviewer=sonnet, critic=opus
   {{**Which model runs each em sub-agent?** Keep this exact line shape, with the defaults shown or
   your own choices. The critic must run on a different model from the implementer; \`critic=codex\`

package/dist/templates.js.map

@@ -1 +1 @@
-{"version":3,"file":"templates.js","sourceRoot":"","sources":["../src/templates.ts"],"names":[],"mappings":"AAAA,+BAA+B;AAC/B,mCAAmC;AAEnC,MAAM,CAAC,MAAM,UAAU,GAAG;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CAiDzB,CAAC;AAEF,wDAAwD;AACxD,EAAE;AACF,2FAA2F;AAC3F,0FAA0F;AAC1F,2FAA2F;AAC3F,2FAA2F;AAC3F,+FAA+F;AAC/F,2FAA2F;AAC3F,2CAA2C;AAE3C,qGAAqG;AACrG,MAAM,CAAC,MAAM,qBAAqB,GAAG;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CA6CpC,CAAC;AAEF,iGAAiG;AACjG,MAAM,CAAC,MAAM,cAAc,GAAG;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CA4E7B,CAAC;AAEF;8BAC8B;AAC9B,MAAM,CAAC,MAAM,qBAAqB,GAAG;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CAuIpC,CAAC;AAEF;oFACoF;AACpF,MAAM,UAAU,YAAY,CAAC,KAAa;IACxC,0FAA0F;IAC1F,yFAAyF;IACzF,6FAA6F;IAC7F,OAAO,UAAU,CAAC,OAAO,CAAC,2BAA2B,EAAE,GAAG,EAAE,CAAC,UAAU,KAAK,GAAG,CAAC,CAAC;AACnF,CAAC;AAED;;;;4DAI4D;AAC5D,MAAM,UAAU,cAAc,CAAC,WAAmB,EAAE,QAAgB;IAClE,6FAA6F;IAC7F,4EAA4E;IAC5E,OAAO,qBAAqB,CAAC,OAAO,CAAC,qBAAqB,EAAE,GAAG,EAAE,CAAC,WAAW,CAAC;SAC3E,OAAO,CAAC,qBAAqB,EAAE,GAAG,EAAE,CAAC,QAAQ,CAAC;SAC9C,OAAO,CACN,oFAAoF,EACpF,yFAAyF,CAC1F,CAAC;AACN,CAAC;AAED;;;;8FAI8F;AAC9F,MAAM,UAAU,iBAAiB,CAAC,WAAmB,EAAE,QAAgB,EAAE,KAAa,EAAE,SAAiB;IACvG,qFAAqF;IACrF,wFAAwF;IACxF,4BAA4B;IAC5B,MAAM,MAAM,GAAG,cAAc,CAAC,OAAO,CAAC,gBAAgB,EAAE,GAAG,EAAE,CAAC,WAAW,CAAC;SACvE,OAAO,CAAC,gBAAgB,EAAE,GAAG,EAAE,CAAC,QAAQ,CAAC;SACzC,OAAO,CAAC,WAAW,EAAE,GAAG,EAAE,CAAC,SAAS,CAAC,CAAC,8DAA8D;SACpG,OAAO,CAAC,kFAAkF,EAAE,UAAU,CAAC;SACvG,OAAO,CAAC,+DAA+D,EAAE,GAAG,CAAC;SAC7E,OAAO,CAAC,gBAAgB,EAAE,KAAK,CAAC,CAAC,8DAA8D;QAChG,oEAAoE;SACnE,OAAO,CAAC,6FAA6F,EAAE,OAAO,CAAC;SAC/G,OAAO,CAAC,cAAc,EAAE,MAAM,CAAC,CAAC,qDAAqD;SACrF,OAAO,CAAC,wDAAwD,EAAE,OAAO,CAAC,CAAC,yBAAyB;SACpG,OAAO,CAAC,2DAA2D,EAAE,OAAO,CAAC,CAAC;IAEjF,OAAO,MAAM;SACV,KAAK,CAAC,IAAI,CAAC;SACX,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,CAAC,IAAI,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC;SACtC,IAAI,CAAC,IAAI,CAAC,CAAC;AAChB,CAAC;AAED;;;;;;;;4CAQ4C;AAC5C,MAAM,UAAU,oBAAoB,CAAC,WAAmB;IACtD,6FAA6F;IAC7F,0FAA0F;IAC1F,wCAAwC;IACxC,OAAO,qBAAqB,CAAC,OAAO,CAAC,kBAAkB,EAAE,GAAG,EAAE,CAAC,WAAW,CAAC,CAAC;AAC9E,CAAC"}
+{"version":3,"file":"templates.js","sourceRoot":"","sources":["../src/templates.ts"],"names":[],"mappings":"AAAA,+BAA+B;AAC/B,mCAAmC;AAEnC,MAAM,CAAC,MAAM,UAAU,GAAG;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CAiDzB,CAAC;AAEF,wDAAwD;AACxD,EAAE;AACF,2FAA2F;AAC3F,0FAA0F;AAC1F,2FAA2F;AAC3F,2FAA2F;AAC3F,+FAA+F;AAC/F,2FAA2F;AAC3F,2CAA2C;AAE3C,qGAAqG;AACrG,MAAM,CAAC,MAAM,qBAAqB,GAAG;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CA6CpC,CAAC;AAEF,iGAAiG;AACjG,MAAM,CAAC,MAAM,cAAc,GAAG;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CA4E7B,CAAC;AAEF;8BAC8B;AAC9B,MAAM,CAAC,MAAM,qBAAqB,GAAG;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CAqIpC,CAAC;AAEF;oFACoF;AACpF,MAAM,UAAU,YAAY,CAAC,KAAa;IACxC,0FAA0F;IAC1F,yFAAyF;IACzF,6FAA6F;IAC7F,OAAO,UAAU,CAAC,OAAO,CAAC,2BAA2B,EAAE,GAAG,EAAE,CAAC,UAAU,KAAK,GAAG,CAAC,CAAC;AACnF,CAAC;AAED;;;;4DAI4D;AAC5D,MAAM,UAAU,cAAc,CAAC,WAAmB,EAAE,QAAgB;IAClE,6FAA6F;IAC7F,4EAA4E;IAC5E,OAAO,qBAAqB,CAAC,OAAO,CAAC,qBAAqB,EAAE,GAAG,EAAE,CAAC,WAAW,CAAC;SAC3E,OAAO,CAAC,qBAAqB,EAAE,GAAG,EAAE,CAAC,QAAQ,CAAC;SAC9C,OAAO,CACN,oFAAoF,EACpF,yFAAyF,CAC1F,CAAC;AACN,CAAC;AAED;;;;8FAI8F;AAC9F,MAAM,UAAU,iBAAiB,CAAC,WAAmB,EAAE,QAAgB,EAAE,KAAa,EAAE,SAAiB;IACvG,qFAAqF;IACrF,wFAAwF;IACxF,4BAA4B;IAC5B,MAAM,MAAM,GAAG,cAAc,CAAC,OAAO,CAAC,gBAAgB,EAAE,GAAG,EAAE,CAAC,WAAW,CAAC;SACvE,OAAO,CAAC,gBAAgB,EAAE,GAAG,EAAE,CAAC,QAAQ,CAAC;SACzC,OAAO,CAAC,WAAW,EAAE,GAAG,EAAE,CAAC,SAAS,CAAC,CAAC,8DAA8D;SACpG,OAAO,CAAC,kFAAkF,EAAE,UAAU,CAAC;SACvG,OAAO,CAAC,+DAA+D,EAAE,GAAG,CAAC;SAC7E,OAAO,CAAC,gBAAgB,EAAE,KAAK,CAAC,CAAC,8DAA8D;QAChG,oEAAoE;SACnE,OAAO,CAAC,6FAA6F,EAAE,OAAO,CAAC;SAC/G,OAAO,CAAC,cAAc,EAAE,MAAM,CAAC,CAAC,qDAAqD;SACrF,OAAO,CAAC,wDAAwD,EAAE,OAAO,CAAC,CAAC,yBAAyB;SACpG,OAAO,CAAC,2DAA2D,EAAE,OAAO,CAAC,CAAC;IAEjF,OAAO,MAAM;SACV,KAAK,CAAC,IAAI,CAAC;SACX,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,CAAC,IAAI,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC;SACtC,IAAI,CAAC,IAAI,CAAC,CAAC;AAChB,CAAC;AAED;;;;;;;;4CAQ4C;AAC5C,MAAM,UAAU,oBAAoB,CAAC,WAAmB;IACtD,6FAA6F;IAC7F,0FAA0F;IAC1F,wCAAwC;IACxC,OAAO,qBAAqB,CAAC,OAAO,CAAC,kBAAkB,EAAE,GAAG,EAAE,CAAC,WAAW,CAAC,CAAC;AAC9E,CAAC"}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@milehimikey/em",
-  "version": "1.14.2",
+  "version": "1.16.0",
   "description": "AI-friendly Event Modeling — a slice-first text DSL rendered to a strict, self-contained Graphviz grid (SVG/PNG)",
   "type": "module",
   "bin": {

package/plugin/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "em",
-  "version": "1.14.2",
+  "version": "1.16.0",
   "description": "Event Modeling with em: discover, design, implement, conform, review and engagement skills over a slice-first text DSL, plus the em MCP server.",
   "author": {
     "name": "Mike Key"
@@ -10,7 +10,7 @@
       "command": "npx",
       "args": [
         "-y",
-        "@milehimikey/em@1.14.2",
+        "@milehimikey/em@1.16.0",
         "mcp"
       ]
     }

package/plugin/agents/em-implementer.md

@@ -1,6 +1,6 @@
 ---
 name: em-implementer
-description: Implements exactly one ratified event-modeling slice in an assigned worktree and branch and opens its pull request; the engagement skill dispatches it once per slice with only the slice key and the worktree path.
+description: Implements exactly one ratified event-modeling slice in an assigned worktree and branch and opens its pull request; the engagement skill dispatches it once per slice with only the slice key, the worktree path and, when there is one, a tracking key.
 tools: Read, Write, Edit, Bash, Grep, Glob, Skill
 ---
 <!-- GENERATED FILE from .claude/agents/em-implementer.md by scripts/build-plugin.ts — do not hand-edit; run npm run docs:generate -->
@@ -19,6 +19,16 @@ You are the em implementer. You build one slice, in one worktree, on one branch,
 - Write code and tests inside that slice's package, as the constitution's layout rule describes it.
 - Every invariant and scenario in the slice doc gets a test that cites its `INV-*` id.
 
+## Tracking key
+
+If your prompt carries a tracking key (an issue-tracker key such as `PROJ-123`, or a URL), the lead has already resolved it for this slice: the slice doc's own `tracking:` wins over the engagement's. Use it as given:
+
+- Title the pull request `<key>: <slice name>`.
+- Cite it in the pull request body.
+- Put it in a commit message only when the constitution's commit convention asks for a ticket key.
+
+With no tracking key, title the pull request as you would without one and invent none.
+
 ## Hard lines
 
 - Never edit the slice doc, the `.em` model, another slice's package, shared infrastructure, or the engagement file.
@@ -30,6 +40,6 @@ You are the em implementer. You build one slice, in one worktree, on one branch,
 
 Reply with:
 
-- The pull request URL.
+- The pull request URL (its title carries the tracking key when you were given one).
 - A per-invariant test map: one line per `INV-*` id, `INV-<id> -> <test file>::<test name>`.
 - Any gap you stopped on, stated as the doc line and the question.

package/plugin/agents/em-validator.md

@@ -10,7 +10,7 @@ You are the em validator. You run checks and report what they say. You make no j
 
 ## Scope
 
-You were given a slice key and the worktree path of its pull request. You read output; you never change anything. Use Bash only to run the checks below and read-only git or `gh` commands. Do not write, edit, create, delete, commit, or push anything.
+You were given a slice key and the worktree path of its pull request, and, when the slice has one, a tracking key. You read output; you never change anything. Use Bash only to run the checks below and read-only git or `gh` commands. Do not write, edit, create, delete, commit, or push anything.
 
 ## Checks
 
@@ -22,6 +22,7 @@ Run each one and record pass or fail:
 4. Diff footprint: every changed path sits inside the slice's package, as the constitution's layout rule describes it. This is a judgment against that rule; quote the rule and list any path outside it.
 5. No diff under `slices/**`, `*.em`, `constitution.md`, or `engagements/`. Use `git diff --name-only <base>...HEAD`.
 6. The pull request body cites the slice doc.
+7. Only when a tracking key was given: the pull request title carries it (`gh pr view <pr> --json title`; the title starts with `<key>:`). Without a tracking key, skip this check and say so.
 
 ## Output