Automations and translations
Purpose
Decide which work the system does on its own, which outside facts it accepts, and what that work
guarantees. Then write it as Automation and Translate slices that say truthfully what is
protected, what is only recorded, and who acts. Grammar depth is in
cratis-screenplay-captures-and-reactions; this skill owns the decisions.
Translation crosses an application boundary: private-to-private follow-up is
Automation, even if a reactor realizes it. Keep captures in Translate and reactions
to their local facts in separate Automation slices. Read
public events and direction when
choosing direction, folding events or specifying publication: it owns the ESM v9
forms, PLAY0616 and directionless Translate's PLAY0694 split boundary.
Requires Screenplay 4.176.0 or later (screenplay --version) for PLAY0694; older compilers leave that directionless shape unchecked.
One source events capture reads one origin (event store); split several origins.
Requires Screenplay 4.155.0 (screenplay --version) for PLAY0687; older tools leave it unchecked.
Model behavior first; code implements external calls, adapters, actors and refused
target scope. Follow cratis-screenplay-modeling-lifecycle for session discipline
and cratis-screenplay-toolchain for verdicts. Settle input, identity, effect and
pending-work contracts when changing each reaction/capture, not at final review.
Tool and realization facts (read before promising anything)
- V1, V3, V4 and target rendering are separate; name the compiler and never remove
a refused construct. Run
screenplay test or MCP run-specifications for V4.
- Read realization and gap-fill before
promising Automation/Translate delivery (STAGE-ESM-024).
- Invokes have no caller without
runs as. Read captures-and-reactions
invocation identity
for the ESM v10 actor and role/authenticated versus claim/opaque admission.
Atomic production boundaries and source identity
Start new models with application-root reaction batches atomic (ESM v22 or later).
Each trigger occurrence's direct productions and each selected refusal branch are
separate all-or-none batches; invoked commands remain independent. Absence retains
legacy per-fact behavior even at later versions. Assert no failed-batch facts and
unchanged views, not only then error. Requires Stage 4.139.0 for v22 admission
(older: -016); atomic mode stays STAGE-ESM-043. Keep as gap-fill.
Read atomic batches and source mappings
when choosing these boundaries or mapping an invoked identifier from $eventSourceId
(or $eventContext.eventSourceId) instead of copying it into event payload.
Effect guarantees and recovery traps
| Guarantee |
What it promises |
What can show it |
| once-only fact |
CertificateSent exists at most once for an enrolment |
constraint … unique event on the right stream + a violation spec |
| idempotent handling |
asking again gives the caller the same outcome, no new effect |
target behaviour (map "already has the event" to success where intended); the model shows a rejection |
| exactly-once external effect |
the person receives one certificate, the card is charged once |
nothing in the model; only the outside system's dedup or a reconciliation can |
A todo list + reaction + unique constraint proves the first. It does not prove the third:
the send can succeed and the append fail (crash, lost reply, constraint race), and the retry
sends again.
- A specification runs its own slice only: to prove an automation that invokes another slice's command, state
then invokes <Command> with the values passed (ESM v34); that command's own slice states its events. A command spec never states what another slice's reaction appends.
- A reaction cascade is not one transaction: earlier accepted facts stay when a later invoked
command rejects (Screenplay
reactions.md). Design each step to be retried on its own.
- Read
references/effects-and-idempotency.md when specifying redelivery,
then no events or refusal disposition; execution is not external deduplication.
- Replay and recovery redelivery are different. Chronicle
[OnceOnly] skips replays (rewind,
redaction, revision) only, not ordinary catch-up, repeated same-source events or crash
redelivery. Recovery runs the handler normally. It is not a per-source run limit or
deduplication. A receipt keyed by ReactorDelivery.Id identifies the retry. Name both.
Capture data-protection traps
A field left out of map still passes through the capture's working record: omission is not
redaction. Check the append mappings and every resulting event property, and record whether
the target stores raw or last-seen source records and how they are minimized.
Personal data kept in events needs bare pii on its concept and a declared purpose
(see command-surface references/compliance.md); keep the marker
even when it blocks binding. Never record bearer tokens, magic links or signed URLs as facts
(a keyed hash or reference at most), and never put PII on the event-source id.
Product sources
Read references/product-sources.md when checking a claim against the Screenplay, Stage, Arc or Chronicle sources.
Requires Screenplay 4.125.0 or later (screenplay --version) for reaction runs as system role (ESM v10).
Requires Arc 20.56.0 or later for [ExecuteCommandsAsSystem].
Requires Arc 22.72.0 or later for a reactor that returns events and commands together; before it, a mixed return is not handled. Stage still refuses a reaction that both produces and invokes (STAGE-ESM-037), so a mixed reaction stays authorized gap-fill whatever the Arc release.
Requires Screenplay 4.105.0 or later (screenplay --version) for list queries (=> Item[]); before it a list query is refused with PLAY0268.
Requires Screenplay 4.124.0 or later (screenplay --version) for --check privilege (PLAY0652).
Read SKILL.md in cratis-screenplay-toolchain when selecting a tool; read the installed versions with screenplay --version and cratis --version. Reverify before claiming
another version behaves the same.
When / when not
- Use: "when X happens, then ...", schedules, retries, work queues, notifications, webhooks, APIs,
files or message feeds, events imported from another context, legacy sync, lifecycles and
longer processes.
- A lifecycle (where one thing is and what moves it on) is a
statemachine; a process that
sends several commands, waits, asks for approval or gives up after a deadline is a
workflow (ESM v36). Read
state machines and workflows before modeling either.
- Not for: reaction, trigger or CDL grammar (
cratis-screenplay-captures-and-reactions); stream
identity and invariants (cratis-screenplay-streams-and-consistency); UI interactions such as
on click (cratis-screenplay-ui-composition); hand-written reactors (cratis-chronicle-reactor).
Interview phase
Skip if the user already gave: every external system with its record types, a sanitized sample
of each, and how each record finds our entity (the correlation strategy); and for automations, the
occurrence, the effect and who acts. Cite existing answers instead of asking again. Missing
correlation is the most common cause of failed integrations: surface it first.
Read integration interview prompts when
sources, mapping, automation ownership or recovery are unsettled. Ask one group at
a time; treat "unsure" as an open question.
Unattended: assume visibly. Record each assumption as a labelled open decision in STATE.md
(.ai-work/screenplay/<model-slug>/STATE.md), mark the dependent slice open, never write a mapping
or actor that nobody confirmed. Read references/worked-integration.md when you need a transcript-shaped example of the integration interview, correlation, translation rules, scenarios, and recovery output.
Procedure
- Inventory. List every reaction, trigger and external source/type in scope; read their
declarations, mappings, descriptions and specs. For integrations resolve only the unknowns
(
references/integration-contracts.md).
- Is it an automation? Write four lines: occurrence (event, clock, application trigger), state
consulted, condition, effect. Always fires, consults nothing, cannot fail, touches nothing outside:
co-production, the command produces both facts. Otherwise continue (
references/automation-patterns.md; a process with waits, approvals, compensation or fan-out: its §10).
- Queue or direct? A todo list (a read model whose membership is the pending work) when work can
wait, retry, fail or need people. Name each opening and closing fact (result, cancellation,
supersession), the work-item key and the recovery path. Direct reaction only for an immediate,
internal, always-possible effect; say why no pending state is needed. A translation is not
automatically infallible.
- Effect and actor.
produces <Fact> records a decided fact; invokes <Command>
requests a decision. Keep its gate and declare the trusted role with reaction
runs as system role "<Role>" (ESM v10). An undeclared actor remains caller-less.
CLI/Stage realization is a separate gap; a returned-command reactor uses
[ExecuteCommandsAsSystem("<role>")] and the matching policy. Never strip a
gate or supply given caller as a fictional reaction identity. Arc supplies a
system principal only to reactors marked [ExecuteCommandsAsSystem]; without
it there is no principal and [Authorize]/[Roles] deny. runs as covers returned
or invoked commands, not imperative pipeline calls, reads, productions or causation.
Run --check privilege --warnaserror (PLAY0652) for
confused-deputy paths: every trigger-event producer must require all declared
system roles. Ungated commands/captures/reaction productions warn; opaque gates
are information, not proven safe. An OR alternative does not require a role.
Clock/application triggers have no producer and are silent; still review trust.
- Trace inputs. Every trigger value, command input, event property and destination needs a
supported source; every filter a business reason. Gaps are questions, not invented mappings.
- Repetition and termination. Identify one logical work occurrence and what a retry is. Guard the
result fact with
constraint ... unique event on the right stream only when once per source is the
rule. Name what ends each chain and check cycles. Answer separately how the external effect avoids
repeating and how replay differs from recovery redelivery (references/effects-and-idempotency.md).
- Translate outside facts (
references/translation-patterns.md): enter only via capture or a
translator reaction, in a Translate slice; correlate first; keep the external fact distinct from
ours; trace source fields and every required target field; decide dedup, ordering and recovery
ownership. A reaction to a capture's local fact is a separate Automation, not a
second job inside Translate. A worker after translation needs a distinct local decision, obligation or effect.
- Specify and audit. Work through
references/cases-to-specify.md per declaration and hand the
named cases to cratis-screenplay-scenario-coverage. Produce the audit in references/audit-format.md.
Rules
Compiler contracts (diagnostics)
- No inline
produces event in a reaction (PLAY0474); declare reaction-produced events in the slice.
- Effects sit under a trigger;
description, where and current runs as are reaction-level; one where per
reaction (PLAY0252); a trigger may not repeat (PLAY0253).
- Clock triggers take no values (PLAY0450) and no
by on reads (PLAY0443). for each <View> is
reserved, not available.
- Capture
when cannot mix and and or (PLAY0089). A capture without key does not bind.
- For
source events, key is a required property on every from event (PLAY0700);
specs supply given <Event> / when append <Event>, not capture records (PLAY0701).
- First sight is
added only. Use when added separately for initial facts; seed
record updates with given capture of the same key. Read captures-and-reactions
references/record-capture-specifications.md for the prerequisite and child/nested rules.
- Current V1 warns on undeclared capture/removal events (PLAY0166); V3 remains a
separate binder check.
- A trigger with
reads that produces directly fails binding: decide in a command.
Command reads can protect with command reads protected and admitted shapes (v25);
trigger reads cannot. Stage 4.138.0 renders protected reads as Arc read protection (cratis render gets it from the first CLI that bundles it; CLI 3.75.0 refuses them with STAGE-ESM-044);
semantic execution is separate from generated-app protection.
- An authorized command exercised in a spec without
given caller is PLAY0389 at binding.
- A list query (
=> Item[]) binds (a snapshot list is not rendered, STAGE-ESM-010);
a clock sweep that iterates items needs a code body the reference does not run
(references/todo-list-example.md).
Modeling defaults (deviate with a recorded reason)
- A
produces without for lands on the triggering fact's source; clock and trigger occurrences have
none, so give for (a carried value or a literal).
where guards every trigger of the reaction and must resolve from each trigger's values: give a clock
sweep its own reaction.
- Malformed or unmappable input becomes a recorded failure fact or dead-letter view, never a dropped
record. A fan-out records one outcome per item; partial success is failure at an effect boundary
(
cratis-engineering-effect-boundaries), never a batch "done" while members failed.
- Infrastructure (logging, caching, retries, outbox plumbing) is never a Translate slice.
- Personal data kept in events needs
pii on its concept; keep it even when it blocks binding or render.
- Code bodies (
file, inline fences) document realization; no local engine runs them.
Review questions
- What stops this from running twice? Forever? When the external call times out?
- Who is the actor, and could an outsider reach the invoked command?
- What does a person see while the work is pending or failed?
- What happens if the outside fact arrives before ours, twice, out of order, or changed?
Gate
Not done until, for every affected reaction and capture, there is a line in the audit
(references/audit-format.md) with a location and a result of complete, open or blocked, and any
unreviewed scope is named. Open decisions and target requirements are in STATE.md. A missing required or
referenced queue opening or closing fact is an unresolved dependency, never skipped silently; a
direct effect states "not applicable: no queue" with its reason (per-chain questions in
references/audit-format.md).
Never report a verdict without the tool and version that produced it.
Verify
- V1 and V3 per
cratis-screenplay-toolchain, each with tool and version. When the bundled compiler stops before v6,
report "V3 blocked: PLAY0268 (ESM v6)". Current admitted scenarios use
standalone screenplay test/MCP for V4; unsupported or unbound is not passed.
- For each external source and type: its translation, or an explicit out-of-scope reason; check
target-field completeness as well as source-field dispositions.
- One happy path is not coverage: cite the spec or the missing case for each branch, denial, competing
claim and closing event.
- Every complete example compiles. Read
references/todo-list-example.md when modeling a pending-work automation (its design-only excerpts insert into assets/pending-certificates.play and assets/retry-sweep.play), and references/translate-example.md when modeling capture plus translator reactions.
Route near misses
Read references/neighbouring-skills.md when the work is grammar, streams, specifications, rendering, legacy writes or hand-written reactors.
Lineage
Read references/provenance.md when checking sources, adaptations, attribution, or approaches deliberately not adopted.
1---2name: cratis-screenplay-automations-and-translations3description: Use when deciding Screenplay event-driven work, schedules, queues or translation of outside facts and their recovery guarantees. Not for reaction, trigger or capture grammar alone; use cratis-screenplay-captures-and-reactions.4license: MIT5metadata:6 source: https://skillmd.com/skills/cratis/cratis-screenplay-automations-and-translations7---89# Automations and translations1011## Purpose12Decide which work the system does on its own, which outside facts it accepts, and what that work13guarantees. Then write it as `Automation` and `Translate` slices that say truthfully what is14protected, what is only recorded, and who acts. Grammar depth is in15`cratis-screenplay-captures-and-reactions`; this skill owns the decisions.1617**Translation crosses an application boundary:** private-to-private follow-up is18Automation, even if a reactor realizes it. Keep captures in Translate and reactions19to their local facts in separate Automation slices. Read20[public events and direction](references/public-events-and-direction.md) when21choosing direction, folding events or specifying publication: it owns the ESM v922forms, PLAY0616 and directionless Translate's PLAY0694 split boundary.23Requires Screenplay 4.176.0 or later (`screenplay --version`) for PLAY0694; older compilers leave that directionless shape unchecked.24One `source events` capture reads one origin (event store); split several origins.25Requires Screenplay 4.155.0 (`screenplay --version`) for PLAY0687; older tools leave it unchecked.2627Model behavior first; code implements external calls, adapters, actors and refused28target scope. Follow `cratis-screenplay-modeling-lifecycle` for session discipline29and `cratis-screenplay-toolchain` for verdicts. Settle input, identity, effect and30pending-work contracts when changing each reaction/capture, not at final review.3132## Tool and realization facts (read before promising anything)33- V1, V3, V4 and target rendering are separate; name the compiler and never remove34 a refused construct. Run `screenplay test` or MCP `run-specifications` for V4.35- Read [realization and gap-fill](references/realization-and-gap-fill.md) before36 promising Automation/Translate delivery (STAGE-ESM-024).37- Invokes have no caller without `runs as`. Read captures-and-reactions38 [invocation identity](../cratis-screenplay-captures-and-reactions/references/invocation-identity.md)39 for the ESM v10 actor and role/authenticated versus claim/opaque admission.4041## Atomic production boundaries and source identity4243Start new models with application-root `reaction batches atomic` (ESM v22 or later).44Each trigger occurrence's direct productions and each selected refusal branch are45separate all-or-none batches; invoked commands remain independent. Absence retains46legacy per-fact behavior even at later versions. Assert no failed-batch facts and47unchanged views, not only `then error`. Requires Stage 4.139.0 for v22 admission48(older: -016); atomic mode stays STAGE-ESM-043. Keep as gap-fill.49Read [atomic batches and source mappings](../cratis-screenplay-captures-and-reactions/references/atomic-batches-and-source-mappings.md)50when choosing these boundaries or mapping an invoked identifier from `$eventSourceId`51(or `$eventContext.eventSourceId`) instead of copying it into event payload.5253## Effect guarantees and recovery traps54| Guarantee | What it promises | What can show it |55|---|---|---|56| **once-only fact** | `CertificateSent` exists at most once for an enrolment | `constraint … unique event` on the right stream + a violation spec |57| **idempotent handling** | asking again gives the caller the same outcome, no new effect | target behaviour (map "already has the event" to success where intended); the model shows a rejection |58| **exactly-once external effect** | the person receives one certificate, the card is charged once | nothing in the model; only the outside system's dedup or a reconciliation can |5960A todo list + reaction + unique constraint proves the first. It does **not** prove the third:61the send can succeed and the append fail (crash, lost reply, constraint race), and the retry62sends again.6364- A specification runs its own slice only: to prove an automation that invokes another slice's command, state `then invokes <Command>` with the values passed (ESM v34); that command's own slice states its events. A command spec never states what another slice's reaction appends.65- A reaction cascade is not one transaction: earlier accepted facts stay when a later invoked66 command rejects (Screenplay `reactions.md`). Design each step to be retried on its own.67- Read `references/effects-and-idempotency.md` when specifying redelivery,68 `then no events` or refusal disposition; execution is not external deduplication.69- Replay and recovery redelivery are different. Chronicle `[OnceOnly]` skips replays (rewind,70 redaction, revision) only, not ordinary catch-up, repeated same-source events or crash71 redelivery. Recovery runs the handler normally. It is not a per-source run limit or72 deduplication. A receipt keyed by `ReactorDelivery.Id` identifies the retry. Name both.7374## Capture data-protection traps75A field left out of `map` still passes through the capture's working record: omission is not76redaction. Check the append mappings and every resulting event property, and record whether77the target stores raw or last-seen source records and how they are minimized.78Personal data kept in events needs bare `pii` on its concept and a declared purpose79(see command-surface `references/compliance.md`); keep the marker80even when it blocks binding. Never record bearer tokens, magic links or signed URLs as facts81(a keyed hash or reference at most), and never put PII on the event-source id.8283## Product sources84Read [references/product-sources.md](references/product-sources.md) when checking a claim against the Screenplay, Stage, Arc or Chronicle sources.8586Requires Screenplay 4.125.0 or later (`screenplay --version`) for reaction `runs as system role` (ESM v10).8788Requires Arc 20.56.0 or later for `[ExecuteCommandsAsSystem]`.8990Requires Arc 22.72.0 or later for a reactor that returns events and commands together; before it, a mixed return is not handled. Stage still refuses a reaction that both `produces` and `invokes` (`STAGE-ESM-037`), so a mixed reaction stays authorized gap-fill whatever the Arc release.9192Requires Screenplay 4.105.0 or later (`screenplay --version`) for list queries (`=> Item[]`); before it a list query is refused with PLAY0268.9394Requires Screenplay 4.124.0 or later (`screenplay --version`) for `--check privilege` (PLAY0652).9596Read `SKILL.md` in `cratis-screenplay-toolchain` when selecting a tool; read the installed versions with `screenplay --version` and `cratis --version`. Reverify before claiming97another version behaves the same.9899## When / when not100- Use: "when X happens, then ...", schedules, retries, work queues, notifications, webhooks, APIs,101 files or message feeds, events imported from another context, legacy sync, lifecycles and102 longer processes.103- A lifecycle (where one thing is and what moves it on) is a `statemachine`; a process that104 sends several commands, waits, asks for approval or gives up after a deadline is a105 `workflow` (ESM v36). Read106 [state machines and workflows](references/statemachines-and-workflows.md) before modeling either.107- Not for: reaction, trigger or CDL grammar (`cratis-screenplay-captures-and-reactions`); stream108 identity and invariants (`cratis-screenplay-streams-and-consistency`); UI interactions such as109 `on click` (`cratis-screenplay-ui-composition`); hand-written reactors (`cratis-chronicle-reactor`).110111## Interview phase112**Skip if** the user already gave: every external system with its record types, a sanitized sample113of each, and how each record finds our entity (the correlation strategy); and for automations, the114occurrence, the effect and who acts. Cite existing answers instead of asking again. Missing115correlation is the most common cause of failed integrations: surface it first.116117Read [integration interview prompts](references/integration-interview.md) when118sources, mapping, automation ownership or recovery are unsettled. Ask one group at119a time; treat "unsure" as an open question.120121**Unattended:** assume visibly. Record each assumption as a labelled open decision in `STATE.md`122(`.ai-work/screenplay/<model-slug>/STATE.md`), mark the dependent slice open, never write a mapping123or actor that nobody confirmed. Read `references/worked-integration.md` when you need a transcript-shaped example of the integration interview, correlation, translation rules, scenarios, and recovery output.124125## Procedure1261. **Inventory.** List every reaction, trigger and external source/type in scope; read their127 declarations, mappings, descriptions and specs. For integrations resolve only the unknowns128 (`references/integration-contracts.md`).1292. **Is it an automation?** Write four lines: occurrence (event, clock, application trigger), state130 consulted, condition, effect. Always fires, consults nothing, cannot fail, touches nothing outside:131 co-production, the command produces both facts. Otherwise continue (`references/automation-patterns.md`; a process with waits, approvals, compensation or fan-out: its §10).1323. **Queue or direct?** A todo list (a read model whose membership is the pending work) when work can133 wait, retry, fail or need people. Name each opening and closing fact (result, cancellation,134 supersession), the work-item key and the recovery path. Direct reaction only for an immediate,135 internal, always-possible effect; say why no pending state is needed. A translation is not136 automatically infallible.1374. **Effect and actor.** `produces <Fact>` records a decided fact; `invokes <Command>`138 requests a decision. Keep its gate and declare the trusted role with reaction139 `runs as system role "<Role>"` (ESM v10). An undeclared actor remains caller-less.140 CLI/Stage realization is a separate gap; a returned-command reactor uses141 `[ExecuteCommandsAsSystem("<role>")]` and the matching policy. Never strip a142 gate or supply `given caller` as a fictional reaction identity. Arc supplies a143 system principal only to reactors marked `[ExecuteCommandsAsSystem]`; without144 it there is no principal and `[Authorize]`/`[Roles]` deny. `runs as` covers returned145 or invoked commands, not imperative pipeline calls, reads, productions or causation.146 Run `--check privilege --warnaserror` (PLAY0652) for147 confused-deputy paths: every trigger-event producer must require **all** declared148 system roles. Ungated commands/captures/reaction productions warn; opaque gates149 are information, not proven safe. An OR alternative does not require a role.150 Clock/application triggers have no producer and are silent; still review trust.1515. **Trace inputs.** Every trigger value, command input, event property and destination needs a152 supported source; every filter a business reason. Gaps are questions, not invented mappings.1536. **Repetition and termination.** Identify one logical work occurrence and what a retry is. Guard the154 result fact with `constraint ... unique event` on the right stream only when once per source is the155 rule. Name what ends each chain and check cycles. Answer separately how the *external* effect avoids156 repeating and how replay differs from recovery redelivery (`references/effects-and-idempotency.md`).1577. **Translate outside facts** (`references/translation-patterns.md`): enter only via `capture` or a158 translator reaction, in a `Translate` slice; correlate first; keep the external fact distinct from159 ours; trace source fields *and* every required target field; decide dedup, ordering and recovery160 ownership. A reaction to a capture's local fact is a separate Automation, not a161 second job inside Translate. A worker after translation needs a distinct local decision, obligation or effect.1628. **Specify and audit.** Work through `references/cases-to-specify.md` per declaration and hand the163 named cases to `cratis-screenplay-scenario-coverage`. Produce the audit in `references/audit-format.md`.164165## Rules166**Compiler contracts** (diagnostics)167- No inline `produces event` in a reaction (PLAY0474); declare reaction-produced events in the slice.168- Effects sit under a trigger; `description`, `where` and current `runs as` are reaction-level; one `where` per169 reaction (PLAY0252); a trigger may not repeat (PLAY0253).170- Clock triggers take no values (PLAY0450) and no `by` on reads (PLAY0443). `for each <View>` is171 reserved, not available.172- Capture `when` cannot mix `and` and `or` (PLAY0089). A capture without `key` does not bind.173- For `source events`, `key` is a required property on every `from` event (PLAY0700);174 specs supply `given <Event>` / `when append <Event>`, not capture records (PLAY0701).175- First sight is `added` only. Use `when added` separately for initial facts; seed176 record updates with `given capture` of the same key. Read captures-and-reactions177 `references/record-capture-specifications.md` for the prerequisite and child/nested rules.178- Current V1 warns on undeclared capture/removal events (PLAY0166); V3 remains a179 separate binder check.180- A trigger with `reads` that `produces` directly fails binding: decide in a command.181 Command reads can protect with `command reads protected` and admitted shapes (v25);182 trigger reads cannot. Stage 4.138.0 renders protected reads as Arc read protection (`cratis render` gets it from the first CLI that bundles it; CLI 3.75.0 refuses them with STAGE-ESM-044);183 semantic execution is separate from generated-app protection.184- An authorized command exercised in a spec without `given caller` is PLAY0389 at binding.185- A list query (`=> Item[]`) binds (a snapshot list is not rendered, `STAGE-ESM-010`);186 a clock sweep that iterates items needs a code body the reference does not run187 (`references/todo-list-example.md`).188189**Modeling defaults** (deviate with a recorded reason)190- A `produces` without `for` lands on the triggering fact's source; clock and trigger occurrences have191 none, so give `for` (a carried value or a literal).192- `where` guards every trigger of the reaction and must resolve from each trigger's values: give a clock193 sweep its own reaction.194- Malformed or unmappable input becomes a recorded failure fact or dead-letter view, never a dropped195 record. A fan-out records one outcome per item; partial success is failure at an effect boundary196 (`cratis-engineering-effect-boundaries`), never a batch "done" while members failed.197- Infrastructure (logging, caching, retries, outbox plumbing) is never a Translate slice.198- Personal data kept in events needs `pii` on its concept; keep it even when it blocks binding or render.199- Code bodies (`file`, inline fences) document realization; no local engine runs them.200201**Review questions**202- What stops this from running twice? Forever? When the external call times out?203- Who is the actor, and could an outsider reach the invoked command?204- What does a person see while the work is pending or failed?205- What happens if the outside fact arrives before ours, twice, out of order, or changed?206207## Gate208Not done until, for every affected reaction and capture, there is a line in the audit209(`references/audit-format.md`) with a location and a result of complete, open or blocked, and any210unreviewed scope is named. Open decisions and target requirements are in `STATE.md`. A missing required or211referenced queue opening or closing fact is an unresolved dependency, never skipped silently; a212direct effect states "not applicable: no queue" with its reason (per-chain questions in213`references/audit-format.md`).214Never report a verdict without the tool and version that produced it.215216## Verify217- V1 and V3 per `cratis-screenplay-toolchain`, each with tool and version. When the bundled compiler stops before v6,218 report "V3 blocked: PLAY0268 (ESM v6)". Current admitted scenarios use219 standalone `screenplay test`/MCP for V4; unsupported or unbound is not passed.220- For each external source and type: its translation, or an explicit out-of-scope reason; check221 target-field completeness as well as source-field dispositions.222- One happy path is not coverage: cite the spec or the missing case for each branch, denial, competing223 claim and closing event.224- Every complete example compiles. Read `references/todo-list-example.md` when modeling a pending-work automation (its design-only excerpts insert into `assets/pending-certificates.play` and `assets/retry-sweep.play`), and `references/translate-example.md` when modeling capture plus translator reactions.225226## Route near misses227Read [references/neighbouring-skills.md](references/neighbouring-skills.md) when the work is grammar, streams, specifications, rendering, legacy writes or hand-written reactors.228229## Lineage230Read `references/provenance.md` when checking sources, adaptations, attribution, or approaches deliberately not adopted.