# Cc Linear > > - **Type:** Skill - **Install:** `agentstack add skill-alexandrbasis-claudops-cc-linear` - **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior - **Seller:** [alexandrbasis](https://agentstack.voostack.com/s/alexandrbasis) - **Installs:** 0 - **Category:** [Productivity](https://agentstack.voostack.com/c/productivity) - **Latest version:** 0.1.0 - **License:** MIT - **Upstream author:** [alexandrbasis](https://github.com/alexandrbasis) - **Source:** https://github.com/alexandrbasis/claudops/tree/main/.claude/skills/cc-linear ## Install ```sh agentstack add skill-alexandrbasis-claudops-cc-linear ``` Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent. ## About # CC Linear > Prefix the first response in a session with a one-line tag: `[cc-linear]`. Interact with Linear via `.claude/scripts/linear-api.sh` — a direct `curl` wrapper over Linear's GraphQL API. Each command is atomic and deterministic. ## Commands ### Issues ```bash .claude/scripts/linear-api.sh get-issue TEAM-66 .claude/scripts/linear-api.sh search "authentication" 5 .claude/scripts/linear-api.sh ai-search "error handling in mobile app" 5 .claude/scripts/linear-api.sh create-issue "Title" "Description" 3 .claude/scripts/linear-api.sh create-issue "Title" "-" 3 <<< "Multiline desc" .claude/scripts/linear-api.sh update-issue TEAM-66 --title "New Title" .claude/scripts/linear-api.sh update-issue TEAM-66 --description "New desc" .claude/scripts/linear-api.sh update-issue TEAM-66 --priority 2 .claude/scripts/linear-api.sh update-status TEAM-66 "In Progress" .claude/scripts/linear-api.sh add-comment TEAM-66 "Comment body" .claude/scripts/linear-api.sh add-comment TEAM-66 "-" <<'EOF' Multiline comment here EOF .claude/scripts/linear-api.sh list-comments TEAM-66 ``` Use `"-"` as the body argument to read from stdin — preferred for any description or comment longer than one line or containing quotes. ### Labels, Assignment & Relations ```bash .claude/scripts/linear-api.sh add-label TEAM-66 "Bug" .claude/scripts/linear-api.sh remove-label TEAM-66 "Bug" .claude/scripts/linear-api.sh assign TEAM-66 "Alexander Basis" .claude/scripts/linear-api.sh add-relation TEAM-66 TEAM-67 "blocks" .claude/scripts/linear-api.sh link-pr TEAM-66 "https://github.com/org/repo/pull/123" ``` ### Listings & Queries ```bash .claude/scripts/linear-api.sh list-issues 10 .claude/scripts/linear-api.sh my-issues # Current user's active issues .claude/scripts/linear-api.sh my-issues 20 # With custom limit .claude/scripts/linear-api.sh list-states .claude/scripts/linear-api.sh list-labels .claude/scripts/linear-api.sh list-users ``` ## Output Formatting The script returns raw JSON. Present results to the user clearly: - **get-issue**: Show identifier, title, status, priority, assignee, labels, and URL - **search / ai-search**: Numbered list with identifier, title, and status - **create-issue**: Confirm with identifier and URL - **update-status / update-issue**: Confirm the change (e.g., "TEAM-66: Todo → In Progress") - **list-comments**: Show author, date, and body for each comment - **my-issues**: Show as a compact table grouped by status - **list-***: Show as a compact table Include the Linear URL in every issue response — the user will want to click through. ## Before Acting Linear mutations are visible to the whole team and send notifications. Before running any of these commands, echo back what you are about to do and wait for confirmation on first use in a session: - `create-issue`, `add-comment`, `add-relation`, `link-pr` (new visible content) - `update-status`, `update-issue`, `assign`, `add-label`, `remove-label` (state changes) Read-only commands (`get-issue`, `search`, `ai-search`, `list-*`, `my-issues`) do not need confirmation — run them freely. For multi-step patterns below, confirm the whole chain once, then execute without re-prompting between steps. ## Configuration | Setting | Value | |---------|-------| | Team Key | `LINEAR_TEAM_KEY` or default `TEAM` | | API Key | `LINEAR_API_KEY` env var | ### Task States (in order) ``` Backlog → Todo → In Progress → In Review → Done | Canceled | Duplicate ``` ### Priority Levels ``` 0: None 1: Urgent 2: High 3: Normal (default) 4: Low ``` ## Workflow Patterns Common multi-step sequences. Each command is atomic. When the steps have no dependency on each other (e.g. adding a label and assigning at the same time), batch them in a single turn; run sequentially only when a later step needs output from an earlier one. ### Start Implementation ```bash .claude/scripts/linear-api.sh update-status TEAM-66 "In Progress" .claude/scripts/linear-api.sh add-comment TEAM-66 "Implementation started. Branch: feature/team-66-feature-name" ``` ### Submit for Review ```bash .claude/scripts/linear-api.sh update-status TEAM-66 "In Review" .claude/scripts/linear-api.sh add-comment TEAM-66 "-" <<'EOF' Implementation completed. - Key changes: [list] - Test coverage: [X]% - PR ready for review. EOF ``` ### Task Done ```bash .claude/scripts/linear-api.sh update-status TEAM-66 "Done" .claude/scripts/linear-api.sh add-comment TEAM-66 "Task completed and PR merged. SHA: abc123" ``` ## Cross-Skill Integration When other skills touch Linear-adjacent work, offer the matching Linear operation as a suggestion — do not run it unprompted. Only execute when the user agrees or when the outer skill explicitly delegates to you. | Skill | When | Linear Action | |-------|------|---------------| | `/ct` | After creating task docs | `create-issue` with task title + link to task doc | | `/si` | On implementation start | `update-status` → "In Progress" + comment with branch | | `/sr` | After code review passes | `update-status` → "In Review" or "Done" | | PR creation | After `gh pr create` | `link-pr` + `update-status` → "In Review" | Don't force these — suggest them when the context is clear (e.g., a TEAM-* ID is visible in the task doc or branch name). ## Error Recovery - If a command fails mid-sequence, retry the failed command — completed steps are idempotent. - If "State not found", run `list-states` to refresh the cache, then retry. - If "Label/User not found", run `list-labels` or `list-users` to check exact names. - Clear all caches: `rm /tmp/linear-TEAM-*.json` - Report command failures (non-zero exits, GraphQL errors) to the user with the exact error message — don't retry hidden. ## References See `references/linear-api-reference.md` for GraphQL queries used by the script. ## Source & license This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code. - **Author:** [alexandrbasis](https://github.com/alexandrbasis) - **Source:** [alexandrbasis/claudops](https://github.com/alexandrbasis/claudops) - **License:** MIT Install and usage instructions live in the source repository linked above. ## Pricing - **Free** — Free ## Security capabilities Automated source analysis of v0.1.0 — what this tool can access: - **Network access:** yes - **Filesystem access:** no - **Shell / process execution:** no - **Environment & secrets:** no - **Dynamic code execution:** no *"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.* ## Versions - **0.1.0** — security scan: passed — Imported from the upstream source. ## Links - Listing page: https://agentstack.voostack.com/l/skill-alexandrbasis-claudops-cc-linear - Seller: https://agentstack.voostack.com/s/alexandrbasis - Browse the marketplace: https://agentstack.voostack.com/browse --- Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.