v2.1.116 (+1,136 tokens)

README.md

@@ -34,7 +34,7 @@ Download it and try it out for free!  **https://piebald.ai/**
 > [!important]
 > **NEW (January 23, 2026): We've added all of Claude Code's ~40 system reminders to this list—see [System Reminders](#system-reminders).**
 
-This repository contains an up-to-date list of all Claude Code's various system prompts and their associated token counts as of **[Claude Code v2.1.114](https://www.npmjs.com/package/@anthropic-ai/claude-code/v/2.1.114) (April 17th, 2026).**  It also contains a [**CHANGELOG.md**](./CHANGELOG.md) for the system prompts across 157 versions since v2.0.14.  From the team behind [<img src="https://github.com/Piebald-AI/piebald/raw/main/assets/logo.svg" width="15"> **Piebald.**](https://piebald.ai/)
+This repository contains an up-to-date list of all Claude Code's various system prompts and their associated token counts as of **[Claude Code v2.1.116](https://www.npmjs.com/package/@anthropic-ai/claude-code/v/2.1.116) (April 20th, 2026).**  It also contains a [**CHANGELOG.md**](./CHANGELOG.md) for the system prompts across 158 versions since v2.0.14.  From the team behind [<img src="https://github.com/Piebald-AI/piebald/raw/main/assets/logo.svg" width="15"> **Piebald.**](https://piebald.ai/)
 
 **This repository is updated within minutes of each Claude Code release.  See the [changelog](./CHANGELOG.md), and follow [@PiebaldAI](https://x.com/PiebaldAI) on X for a summary of the system prompt changes in each release.**
 
@@ -102,7 +102,7 @@ Sub-agents and utilities.
 - [Agent Prompt: Coding session title generator](./system-prompts/agent-prompt-coding-session-title-generator.md) (**181** tks) - Generates a title for the coding session.
 - [Agent Prompt: Conversation summarization](./system-prompts/agent-prompt-conversation-summarization.md) (**1121** tks) - System prompt for creating detailed conversation summaries.
 - [Agent Prompt: Determine which memory files to attach](./system-prompts/agent-prompt-determine-which-memory-files-to-attach.md) (**265** tks) - Agent for determining which memory files to attach for the main agent.
-- [Agent Prompt: Dream memory consolidation](./system-prompts/agent-prompt-dream-memory-consolidation.md) (**763** tks) - Instructs an agent to perform a multi-phase memory consolidation pass — orienting on existing memories, gathering recent signal from logs and transcripts, merging updates into topic files, and pruning the index.
+- [Agent Prompt: Dream memory consolidation](./system-prompts/agent-prompt-dream-memory-consolidation.md) (**802** tks) - Instructs an agent to perform a multi-phase memory consolidation pass — orienting on existing memories, gathering recent signal from logs and transcripts, merging updates into topic files, and pruning the index.
 - [Agent Prompt: Dream memory pruning](./system-prompts/agent-prompt-dream-memory-pruning.md) (**456** tks) - Instructs an agent to perform a memory pruning pass by deleting stale or invalidated memory files and collapsing duplicates in the memory directory.
 - [Agent Prompt: General purpose](./system-prompts/agent-prompt-general-purpose.md) (**285** tks) - System prompt for the general-purpose subagent that searches, analyzes, and edits code across a codebase while reporting findings concisely to the caller.
 - [Agent Prompt: Hook condition evaluator (stop)](./system-prompts/agent-prompt-hook-condition-evaluator-stop.md) (**145** tks) - System prompt for evaluating hook conditions, specifically stop conditions, in Claude Code.
@@ -255,6 +255,7 @@ Text for large system reminders.
 - [System Reminder: Plan mode is active (iterative)](./system-prompts/system-reminder-plan-mode-is-active-iterative.md) (**936** tks) - Iterative plan mode system reminder for main agent with user interviewing workflow.
 - [System Reminder: Plan mode is active (subagent)](./system-prompts/system-reminder-plan-mode-is-active-subagent.md) (**307** tks) - Simplified plan mode system reminder for sub agents.
 - [System Reminder: Plan mode re-entry](./system-prompts/system-reminder-plan-mode-re-entry.md) (**236** tks) - System reminder sent when the user enters Plan mode after having previously exited it either via shift+tab or by approving Claude's plan.
+- [System Reminder: Post-turn session summary](./system-prompts/system-reminder-post-turn-session-summary.md) (**792** tks) - Instructs Claude to produce a structured JSON summary of a Claude Code session for inbox-style triage across multiple sessions.
 - [System Reminder: Session continuation](./system-prompts/system-reminder-session-continuation.md) (**37** tks) - Notification that session continues from another machine.
 - [System Reminder: Stop hook blocking error](./system-prompts/system-reminder-stop-hook-blocking-error.md) (**20** tks) - Error from a blocking hook command.
 - [System Reminder: Task tools reminder](./system-prompts/system-reminder-task-tools-reminder.md) (**123** tks) - Reminder to use task tracking tools.
@@ -343,7 +344,7 @@ Text for large system reminders.
 - [Tool Description: Bash (timeout)](./system-prompts/tool-description-bash-timeout.md) (**83** tks) - Bash tool instruction: optional timeout configuration.
 - [Tool Description: Bash (verify parent directory)](./system-prompts/tool-description-bash-verify-parent-directory.md) (**38** tks) - Bash tool instruction: verify parent directory before creating files.
 - [Tool Description: Bash (working directory)](./system-prompts/tool-description-bash-working-directory.md) (**37** tks) - Bash tool note about working directory persistence and shell state.
-- [Tool Description: SendMessageTool (non-agent-teams)](./system-prompts/tool-description-sendmessagetool-non-agent-teams.md) (**133** tks) - Send a message the user will read, describes this tool well.
+- [Tool Description: SendMessageTool (non-agent-teams)](./system-prompts/tool-description-sendmessagetool-non-agent-teams.md) (**226** tks) - Send a message the user will read, describes this tool well.
 - [Tool Description: Snooze (delay and reason guidance)](./system-prompts/tool-description-snooze-delay-and-reason-guidance.md) (**608** tks) - Extends the snooze tool description with guidance on choosing delaySeconds relative to the 5-minute prompt cache TTL and writing informative reason fields.
 - [Tool Description: TaskList (teammate workflow)](./system-prompts/tool-description-tasklist-teammate-workflow.md) (**133** tks) - Conditional section appended to TaskList tool description.
 - [Tool Description: ToolSearch (second part)](./system-prompts/tool-description-toolsearch-second-part.md) (**202** tks) - The bulk of the tool description.
@@ -363,17 +364,17 @@ Built-in skill prompts for specialized tasks.
 - [Skill: /loop slash command](./system-prompts/skill-loop-slash-command.md) (**969** tks) - Parses user input into an interval and prompt, converts the interval to a cron expression, and schedules a recurring task.
 - [Skill: /stuck slash command](./system-prompts/skill-stuck-slash-command.md) (**964** tks) - Diagnozse frozen or slow Claude Code sessions.
 - [Skill: Agent Design Patterns](./system-prompts/skill-agent-design-patterns.md) (**1974** tks) - Reference guide covering decision heuristics for building agents on the Claude API, including tool surface design, context management, caching strategies, and composing tool calls.
-- [Skill: Build with Claude API (reference guide)](./system-prompts/skill-build-with-claude-api-reference-guide.md) (**591** tks) - Template for presenting language-specific reference documentation with quick task navigation.
+- [Skill: Build with Claude API (reference guide)](./system-prompts/skill-build-with-claude-api-reference-guide.md) (**614** tks) - Template for presenting language-specific reference documentation with quick task navigation.
-- [Skill: Building LLM-powered applications with Claude](./system-prompts/skill-building-llm-powered-applications-with-claude.md) (**8681** tks) - Guides Claude in building LLM-powered applications using the Anthropic SDK, covering language detection, API surface selection (Claude API vs Managed Agents), model defaults, thinking/effort configuration, and language-specific documentation reading.
+- [Skill: Building LLM-powered applications with Claude](./system-prompts/skill-building-llm-powered-applications-with-claude.md) (**8758** tks) - Guides Claude in building LLM-powered applications using the Anthropic SDK, covering language detection, API surface selection (Claude API vs Managed Agents), model defaults, thinking/effort configuration, and language-specific documentation reading.
 - [Skill: Computer Use MCP](./system-prompts/skill-computer-use-mcp.md) (**1206** tks) - Instructions for using computer-use MCP tools including tool selection tiers, app access tiers, link safety, and financial action restrictions.
 - [Skill: Create verifier skills](./system-prompts/skill-create-verifier-skills.md) (**2551** tks) - Prompt for creating verifier skills for the Verify agent to automatically verify code changes.
 - [Skill: Debugging](./system-prompts/skill-debugging.md) (**412** tks) - Instructions for debugging an issue that the user is encountering in the Claude Code session.
 - [Skill: Dynamic pacing loop execution](./system-prompts/skill-dynamic-pacing-loop-execution.md) (**558** tks) - Step-by-step instructions for executing a dynamic pacing loop that runs tasks, arms persistent monitors for event-gated waits, schedules fallback heartbeat ticks, and handles task notifications.
 - [Skill: Generate permission allowlist from transcripts](./system-prompts/skill-generate-permission-allowlist-from-transcripts.md) (**2338** tks) - Analyzes session transcripts to extract frequently used read-only tool-call patterns and adds them to the project's .claude/settings.json permission allowlist to reduce permission prompts.
-- [Skill: Model migration guide](./system-prompts/skill-model-migration-guide.md) (**18052** tks) - Step-by-step instructions for migrating existing code to newer Claude models, covering breaking changes, deprecated parameters, per-SDK syntax, prompt-behavior shifts, and migration checklists.
+- [Skill: Model migration guide](./system-prompts/skill-model-migration-guide.md) (**18104** tks) - Step-by-step instructions for migrating existing code to newer Claude models, covering breaking changes, deprecated parameters, per-SDK syntax, prompt-behavior shifts, and migration checklists.
 - [Skill: Schedule recurring cron and execute immediately (compact)](./system-prompts/skill-schedule-recurring-cron-and-execute-immediately-compact.md) (**173** tks) - Instructions for creating a recurring cron job, confirming the schedule with the user, and immediately executing the parsed prompt without waiting for the first cron fire.
 - [Skill: Schedule recurring cron and run immediately](./system-prompts/skill-schedule-recurring-cron-and-run-immediately.md) (**271** tks) - Converts an interval to a cron expression, schedules a recurring task via the cron creation tool, confirms to the user, and immediately executes the task without waiting for the first cron fire.
-- [Skill: Simplify](./system-prompts/skill-simplify.md) (**877** tks) - Instructions for simplifying code.
+- [Skill: Simplify](./system-prompts/skill-simplify.md) (**937** tks) - Instructions for simplifying code.
 - [Skill: Team onboarding guide](./system-prompts/skill-team-onboarding-guide.md) (**521** tks) - Template for onboarding a new teammate to a team's Claude Code setup, walking them through usage stats, setup checklists, MCP servers, skills, and team tips in a warm conversational style.
 - [Skill: Update Claude Code Config](./system-prompts/skill-update-claude-code-config.md) (**1190** tks) - Skill for modifying Claude Code configuration file (settings.json).
 - [Skill: Verify CLI changes (example for Verify skill)](./system-prompts/skill-verify-cli-changes-example-for-verify-skill.md) (**565** tks) - Example workflow for verifying a CLI change, as part of the Verify skill.

system-prompts/agent-prompt-dream-memory-consolidation.md

@@ -1,7 +1,7 @@
 <!--
 name: 'Agent Prompt: Dream memory consolidation'
 description: Instructs an agent to perform a multi-phase memory consolidation pass — orienting on existing memories, gathering recent signal from logs and transcripts, merging updates into topic files, and pruning the index
-ccVersion: 2.1.98
+ccVersion: 2.1.116
 variables:
   - MEMORY_DIR
   - MEMORY_DIR_CONTEXT
@@ -31,13 +31,13 @@ ${TRANSCRIPT_SOURCE_NOTE}
 - `ls` the memory directory to see what already exists
 - Read `${INDEX_FILE}` to understand the current index
 - Skim existing topic files so you improve them rather than creating duplicates
-- If `logs/` or `sessions/` subdirectories exist (assistant-mode layout), review recent entries there
+- `ls logs/` — recent daily activity logs (one file per day). If a `sessions/` subdirectory also exists, review recent entries there too
 
 ## Phase 2 — Gather recent signal
 
 Look for new information worth persisting. Sources in rough priority order:
 
-1. **Daily logs** (`logs/YYYY/MM/YYYY-MM-DD.md`) if present — these are the append-only stream
+1. **Daily logs** (`logs/YYYY/MM/YYYY-MM-DD.md`) — the append-only activity stream. Read the most recent 1–3 days; each line is prefix-coded (`>` user, `<` assistant, `.` tool call)
 2. **Existing memories that drifted** — facts that contradict something you see in the codebase now
 3. **Transcript search** — if you need specific context (e.g., "what was the error message from yesterday's build failure?"), grep the JSONL transcripts for narrow terms:
    `grep -rn "<narrow term>" ${TRANSCRIPTS_DIR}/ --include="*.jsonl" | tail -50`

system-prompts/agent-prompt-schedule-slash-command.md

@@ -1,7 +1,7 @@
 <!--
 name: 'Agent Prompt: /schedule slash command'
 description: Guides the user through scheduling, updating, listing, or running remote Claude Code agents on cron triggers via the Anthropic cloud API
-ccVersion: 2.1.90
+ccVersion: 2.1.116
 variables:
   - USER_REQUEST
   - ASK_USER_QUESTION_TOOL_NAME
@@ -84,7 +84,7 @@ ${MCP_CONNECTORS_LIST}
 
 When attaching connectors to a trigger, use the `connector_uuid` and `name` shown above (the name is already sanitized to only contain letters, numbers, hyphens, and underscores), and the connector's URL. The `name` field in `mcp_connections` must only contain `[a-zA-Z0-9_-]` — dots and spaces are NOT allowed.
 
-**Important:** Infer what services the agent needs from the user's description. For example, if they say "check Datadog and Slack me errors," the agent needs both Datadog and Slack connectors. Cross-reference against the list above and warn if any required service isn't connected. If a needed connector is missing, direct the user to https://claude.ai/settings/connectors to connect it first.
+**Important:** Infer what services the agent needs from the user's description. For example, if they say "check Datadog and Slack me errors," the agent needs both Datadog and Slack connectors. Cross-reference against the list above and warn if any required service isn't connected. If a needed connector is missing, direct the user to https://claude.ai/customize/connectors to connect it first.
 
 ## Environments
 
@@ -140,7 +140,7 @@ Minimum interval is 1 hour. `*/30 * * * *` will be rejected.
    - Explicit about what actions to take (open PRs, commit, just analyze, etc.)
 3. **Set the schedule** — Ask when and how often. The user's timezone is ${USER_TIMEZONE}. When they say a time (e.g., "every morning at 9am"), assume they mean their local time and convert to UTC for the cron expression. Always confirm the conversion: "9am ${USER_TIMEZONE} = Xam UTC."
 4. **Choose the model** — Default to `claude-sonnet-4-6`. Tell the user which model you're defaulting to and ask if they want a different one.
-5. **Validate connections** — Infer what services the agent will need from the user's description. For example, if they say "check Datadog and Slack me errors," the agent needs both Datadog and Slack MCP connectors. Cross-reference with the connectors list above. If any are missing, warn the user and link them to https://claude.ai/settings/connectors to connect first.${DEFAULT_GIT_REPO_URL?` The default git repo is already set to `${DEFAULT_GIT_REPO_URL}`. Ask the user if this is the right repo or if they need a different one.`:" Ask which git repos the remote agent needs cloned into its environment."}
+5. **Validate connections** — Infer what services the agent will need from the user's description. For example, if they say "check Datadog and Slack me errors," the agent needs both Datadog and Slack MCP connectors. Cross-reference with the connectors list above. If any are missing, warn the user and link them to https://claude.ai/customize/connectors to connect first.${DEFAULT_GIT_REPO_URL?` The default git repo is already set to `${DEFAULT_GIT_REPO_URL}`. Ask the user if this is the right repo or if they need a different one.`:" Ask which git repos the remote agent needs cloned into its environment."}
 6. **Review and confirm** — Show the full configuration before creating. Let them adjust.
 7. **Create it** — Call `${REMOTE_TRIGGER_TOOL_NAME}` with `action: "create"` and show the result. The response includes the trigger ID. Always output a link at the end: `https://claude.ai/code/scheduled/{TRIGGER_ID}`
 

system-prompts/skill-build-with-claude-api-reference-guide.md

@@ -1,7 +1,7 @@
 <!--
 name: 'Skill: Build with Claude API (reference guide)'
 description: Template for presenting language-specific reference documentation with quick task navigation
-ccVersion: 2.1.108
+ccVersion: 2.1.116
 -->
 ## Reference Documentation
 
@@ -17,7 +17,10 @@ The relevant documentation for your detected language is included below in `<doc
 
 **Long-running conversations (may exceed context window):**
 → Refer to `{lang}/claude-api/README.md` — see Compaction section
-<!-- __G2__ -->
+
+**Migrating to a newer model or replacing a retired model:**
+→ Refer to `shared/model-migration.md`
+
 **Prompt caching / optimize caching / "why is my cache hit rate low":**
 → Refer to `shared/prompt-caching.md` + `{lang}/claude-api/README.md` (Prompt Caching section)
 

system-prompts/skill-building-llm-powered-applications-with-claude.md

@@ -1,7 +1,7 @@
 <!--
 name: 'Skill: Building LLM-powered applications with Claude'
 description: Guides Claude in building LLM-powered applications using the Anthropic SDK, covering language detection, API surface selection (Claude API vs Managed Agents), model defaults, thinking/effort configuration, and language-specific documentation reading
-ccVersion: 2.1.111
+ccVersion: 2.1.116
 -->
 # Building LLM-Powered Applications with Claude
 
@@ -34,7 +34,9 @@ For the Claude model version, please use {{OPUS_NAME}}, which you can access via
 
 If the User Request at the bottom of this prompt is a bare subcommand string (no prose), search every **Subcommands** table in this document — including any in sections appended below — and follow the matching Action column directly. This lets users invoke specific flows via `/claude-api <subcommand>`. If no table in the document matches, treat the request as normal prose.
 
-<!-- Subcommand tables are defined per-section below; this header block contains only the dispatch rule so that feature-gated sections can add their own tables without leaking strings into ungated builds. -->
+| Subcommand | Action |
+|---|---|
+| `migrate` | Migrate existing Claude API code to a newer model. **Read `shared/model-migration.md` immediately** and follow it in order: Step 0 (confirm scope — ask which files/directories before any edit), Step 1 (classify each file), then the per-target breaking-changes section. Do not summarize the guide — execute it. If the user did not name a target model, ask which model to migrate to in the same turn as the scope question. |
 
 ---
 

system-prompts/skill-model-migration-guide.md

@@ -1,10 +1,12 @@
 <!--
 name: 'Skill: Model migration guide'
 description: Step-by-step instructions for migrating existing code to newer Claude models, covering breaking changes, deprecated parameters, per-SDK syntax, prompt-behavior shifts, and migration checklists
-ccVersion: 2.1.111
+ccVersion: 2.1.116
 -->
 # Model Migration Guide
 
+> **If you arrived via `/claude-api migrate`:** this is the right file. Execute the steps below in order — do not summarize them back to the user. Start with Step 0 (confirm scope) before touching any file.
+
 How to move existing code to newer Claude models. Covers breaking changes, deprecated parameters, and drop-in replacements for retired models.
 
 For the latest, authoritative version (with code samples in every supported language), WebFetch the **Migration Guide** URL from `shared/live-sources.md`. Use this file for the consolidated, skill-resident reference; fall back to the live docs whenever a model launch or breaking change may have shifted the picture.

system-prompts/skill-simplify.md

@@ -1,7 +1,7 @@
 <!--
 name: 'Skill: Simplify'
 description: Instructions for simplifying code
-ccVersion: 2.1.81
+ccVersion: 2.1.116
 variables:
   - AGENT_TOOL_NAME
 -->
@@ -35,7 +35,8 @@ Review the same changes for hacky patterns:
 4. **Leaky abstractions**: exposing internal details that should be encapsulated, or breaking existing abstraction boundaries
 5. **Stringly-typed code**: using raw strings where constants, enums (string unions), or branded types already exist in the codebase
 6. **Unnecessary JSX nesting**: wrapper Boxes/elements that add no layout value — check if inner component props (flexShrink, alignItems, etc.) already provide the needed behavior
-7. **Unnecessary comments**: comments explaining WHAT the code does (well-named identifiers already do that), narrating the change, or referencing the task/caller — delete; keep only non-obvious WHY (hidden constraints, subtle invariants, workarounds)
+7. **Nested conditionals**: ternary chains (`a ? x : b ? y : ...`), nested if/else, or nested switch 3+ levels deep — flatten with early returns, guard clauses, a lookup table, or an if/else-if cascade
+8. **Unnecessary comments**: comments explaining WHAT the code does (well-named identifiers already do that), narrating the change, or referencing the task/caller — delete; keep only non-obvious WHY (hidden constraints, subtle invariants, workarounds)
 
 ### Agent 3: Efficiency Review
 

system-prompts/system-reminder-post-turn-session-summary.md

@@ -0,0 +1,35 @@
+<!--
+name: 'System Reminder: Post-turn session summary'
+description: Instructs Claude to produce a structured JSON summary of a Claude Code session for inbox-style triage across multiple sessions
+ccVersion: 2.1.116
+variables:
+  - ADDITIONAL_CONTEXT_BLOCK
+  - PREVIOUS_AGENT_SUMMARY
+-->
+<system-reminder>
+You are now producing a post-turn summary for this Claude Code session. Read the conversation that just happened and produce an overview that helps the user triage which of their many sessions need attention, and in what order.
+${ADDITIONAL_CONTEXT_BLOCK}${PREVIOUS_AGENT_SUMMARY}
+IMPORTANT:
+- You have NO tools available — do not attempt to call any tool
+- This is a one-off response — there will be no follow-up turns
+- Respond with ONLY a JSON object on a single line, nothing else (no code fences, no prose)
+
+The JSON must have exactly these fields:
+{"status_category":"blocked|review_ready","status_detail":"...","title":"...","needs_action":"..."}
+
+Formatting: all fields except title accept markdown. Use `backticks` for file names, function names, and shell commands. Use [text](url) for PRs and documents. Keep title plain text.
+
+Frame fields in terms of user-visible behavior. Describe what the user will observe, what now works differently, or what broke or got fixed. Don't over-index on implementation details or specific lines of code unless the user is in the weeds with you — this summary is intentionally high-level. Good: "Login no longer loops on expired tokens", "Settings now sync across restarts".
+
+status_category — pick one based on who unblocks the session next:
+- blocked: Claude hit genuine ambiguity or a missing piece it can't route around — conflicting requirements, an unanswerable design question, context only the user has. NOT for awaiting review or normal handoffs: if Claude produced a deliverable and is waiting for eyes, use review_ready. Blocked indicates that a session is stuck, not waiting further direction or general review.
+- review_ready: Claude produced something the user should look at — a PR, a plan, a diff, a document, a pushed branch, or a conversational answer. This is the default end state; the user (not this classifier) decides when work is "done".
+
+status_detail — A 5-12 word blurb, scannable in an inbox row. Present tense, concrete, names the subject AND the cause in one breath — "Blocked on retry logic merge: three call sites conflict", "PR #1234 ready: tests green, auth code needs review". The reader should know both WHAT state the conversation is currently in, and WHY without opening the session. Present tense, concrete.
+
+title — a short (3-6 words) title shown to the user in a list of all of their sessions. This title should be specific and actionable for the user to distinguish between other streams of work. Name the feature or bug being worked on, not the activity. Ex: "Fix infinite login redirect on /code". Keep this stable — only change this from your previously generated title if the session's focus has shifted. Write as a noun phrase or imperative, no subject.
+
+needs_action — A 5-12 word blurb, scannable in an inbox row. Present tense, concrete, names the subject AND the cause in one breath — "Blocked on retry logic merge: three call sites conflict", "PR #1234 ready: tests green, auth code needs review". The reader should know both WHAT state the conversation is currently in, and WHY without opening the session. Present tense, concrete. Only populate this if the user has an action they should do. Empty string if nothing required.
+
+Respond now with ONLY the JSON object:
+</system-reminder>

system-prompts/tool-description-sendmessagetool-non-agent-teams.md

@@ -1,10 +1,10 @@
 <!--
 name: 'Tool Description: SendMessageTool (non-agent-teams)'
 description: Send a message the user will read, describes this tool well.
-ccVersion: 2.1.73
+ccVersion: 2.1.116
 -->
 Send a message the user will read. Text outside this tool is visible in the detail view, but most won't open it — the answer lives here.
 
-`message` supports markdown. `attachments` takes file paths (absolute or cwd-relative) for images, diffs, logs.
+`message` supports markdown. `attachments` accepts two forms per entry: a file path string (absolute or cwd-relative) for a file you can read here — images, diffs, logs — or the exact {file_uuid, file_name, size, is_image} object a device tool like `attach_file` returned to you. Use the path form when the file is on your working filesystem; use the object form when the user's device already uploaded the file and handed you a reference — pass that object through verbatim, don't try to path it.
 
 `status` labels intent: 'normal' when replying to what they just asked; 'proactive' when you're initiating — a scheduled task finished, a blocker surfaced during background work, you need input on something they haven't asked about. Set it honestly; downstream routing uses it.