Linear Agents (AIG, Signals, Interaction)
This skill should be used when building or registering an agent that operates inside Linear — agent signals, agent interaction, OAuth actor mode, AIG (Agent Intelligence Gateway). Activates on "linear agent", "agent signal", "agent interaction", "linear aig", "agents in linear".
What this skill does
# Linear Agents
References:
- Agents in Linear (user docs): https://linear.app/docs/agents-in-linear
- Agents (developer): https://linear.app/developers/agents
- Agent interaction: https://linear.app/developers/agent-interaction
- Agent signals: https://linear.app/developers/agent-signals
- AIG: https://linear.app/developers/aig
## Agent model
A Linear agent is an OAuth app with the `agents:create` and `agents:signal` scopes that:
- Can be **assigned** to issues (treated as a first-class assignee)
- **Posts** comments / status changes on behalf of users (via OAuth actor authorization)
- **Emits signals** — short status messages rendered inline on the issue ("running tests", "75% complete", "needs input")
- **Receives interaction events** — when a user @-mentions the agent or assigns it
## Registration
Settings → API → Agents → New agent. Or via API once granted `agents:create`. Capture:
- `agentId`
- `agent_oauth_token` (long-lived)
- Webhook URL for interaction events
## Agent interaction
When a user assigns the agent to an issue:
- Linear sends a webhook event of type `Agent` with action `interaction`
- Body includes `issue.id`, `actor` (user who triggered), `kind` (assigned, mentioned, replied)
- Agent should respond by:
1. Acknowledging via `agentSignalCreate({ kind: "progress", message: "Working on it…" })`
2. Doing the work
3. Reporting completion via `agentSignalCreate({ kind: "completion", message: "Done — see comment" })`
4. Posting a comment with the result
## Agent signals
Signals are lightweight status pings that render in the Linear UI as a small badge:
- `progress` — "Running tests..." (yellow)
- `completion` — "Tests passed" (green)
- `request_input` — "Need approval" (blue, with button)
- `error` — "Failed: ..." (red)
```ts
await client.agentSignalCreate({
agentId,
issueId,
kind: "progress",
message: "Compiling…",
metadata: { jobId: "..." }
});
```
Signals are NOT comments — they're ephemeral. Use them for in-progress updates; use comments for permanent results.
## AIG (Agent Intelligence Gateway)
The AIG (https://linear.app/developers/aig) is Linear's gateway for agent-to-agent communication. Use cases:
- Pass context between agents (e.g. linear-issue-curator hands off to harness-linear-bridge)
- Negotiate which agent should handle a multi-agent task
- Aggregate signals from multiple sub-agents
The plugin's `lib/aig.ts` provides:
```ts
export async function aigPublish(channel: string, msg: AIGMessage): Promise<void>;
export function aigSubscribe(channel: string, handler: (msg: AIGMessage) => void): () => void;
```
## Actor authorization in agents
When an agent posts on behalf of a user:
1. Mint an actor token via your backend (signs a JWT with `userId`, 5-min expiry)
2. Include in `Linear-Actor-Token` header
3. The action shows up in Linear's UI as performed by the user, with a small "via Agent: <name>" badge
```ts
const headers = { "Linear-Actor-Token": actorToken };
await fetch("https://api.linear.app/graphql", {
method: "POST",
headers: { ...headers, Authorization: `Bearer ${agentToken}` },
body: JSON.stringify({ query, variables })
});
```
## Best practices
- **Idempotency**: agents may receive the same interaction event twice (e.g. on retry). Dedupe by event ID.
- **Timeouts**: emit a `progress` signal at least every 30s if the work is long-running, otherwise Linear shows "Agent unresponsive".
- **Failure surfaces**: on error, emit `agentSignalCreate({ kind: "error" })` AND post a comment with the failure details. Don't silently fail.
- **Scope minimisation**: don't request `admin` scope unless you genuinely manage workflows.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.