Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/monkilabs/opencastle/linearnpx skills add monkilabs/opencastle --skill lineargit clone --depth 1 https://github.com/monkilabs/opencastleWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00054 | $0.00659 |
| Opus 5 | $0.00027 | $0.00329 |
| Sonnet 5 | $0.00011 | $0.00132 |
| Haiku 4.5 | $0.00005 | $0.00066 |
Grade A, and why
linear-task-management scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Management with Linear
Team ID, workflow state UUIDs, and label UUIDs: tracker-config.md. Docs: https://linear.app/docs
The stateId UUID trap
update_issue requires a workflow state UUID. Passing a display name like "In Progress" always fails with stateId must be a UUID. The names returned by list_issues / get_issue are display-only and are not valid stateId values.
// works — UUID read from tracker-config.md
{ "issueId": "TAS-42", "stateId": "a1b2c3d4-e5f6-7890-abcd-ef1234567890" }
// fails — name, not UUID
{ "issueId": "TAS-42", "status": "In Progress" }
If tracker-config.md has no state UUIDs: skip status updates and log a warning. To populate them, ask the user for Linear Settings → Teams → Workflow (the UUID is in the browser URL per state) or the GraphQL workflowStates { nodes { id name } } query. Labels and teams are UUIDs too (teamId, labelIds).
Other gotchas
- Linear MCP has no comment API. To record a blocker, edit the issue description.
- Treat a create as successful only if it returns an issue ID (
TAS-42) — verify before delegating. - GitHub integration auto-transitions on PR events (push → In Progress, review → In Review, merge → Done), configured in Settings → Team → Pull request automation. Link by putting
TAS-123in the branch or PR title. - On resume, re-read every issue status before acting; a stale local view causes double work.
Conventions
Verb-first titles mapping to intent: Add schema: priceRange to place, Migrate DB: add price_range, Update query: include priceRange, Implement UI: PriceRangeFilter.
Priority: P1 blocks other tasks / critical path, P2 core feature on critical path, P3 parallelizable support work, P4 docs and polish.
Flow Backlog → Todo → In Progress → In Review → Done → Cancelled. Every description carries Objective, Files (partition), Acceptance Criteria, Dependencies (#TAS-XX). Group related issues under a Linear project.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 41 lines · 54 tokens per session scan A 3406e3667277
linear-task-management is a skill published in the GitHub repository monkilabs/opencastle (61 stars, last pushed 4d ago), licensed MIT. It adds 54 tokens to every session and 659 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
find-code-tasks
Lists all code tasks in the repository with their status, dates, and metadata. Useful for getting an overview of pending work or finding specific tasks.
linear
Read Linear issues, transition state, and post comments. The entry point for ticket-driven agent workflows.
multi-module-maven
Use when working in a multi-module Maven project. Covers parent POM conventions, shared dependency management, inter-module rules, and build ordering.
product-architect
Complete product development system with 64 agents and 35 frameworks. Use when the user wants to build a product, write a PRD, plan an MVP or roadmap, design an app, research a market or check whether a feature already exists or is novel, do competitive analysis, run a security audit, build a financial model, plan…
codex-delegation
Use when a coding task would benefit from delegating work to Codex in the background — a deep independent second opinion, security or architecture analysis, or a parallel implementation running while the session continues. Lets Claude drive the codex companion itself (task, review, status --wait, result) without the…
cursor-delegation
Use when a coding task would benefit from delegating work to Cursor in the background — fast parallel implementation, scaffolding, or an everyday review running while the session continues. Lets Claude drive the cursor companion itself (task, review, status --wait, result) without the user typing /cursor: commands.