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/linearis-oss/linearis/linearisnpx skills add linearis-oss/linearis --skill linearisgit clone --depth 1 https://github.com/linearis-oss/linearisWhat 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 | $0.00111 | $0.01125 |
| Opus 5 | $0.00056 | $0.00562 |
| Sonnet 5 | $0.00022 | $0.00225 |
| Haiku 4.5 | $0.00011 | $0.00112 |
Grade A, and why
linearis 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 yesterday.
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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
linearis
Drive Linear.app from the shell via the linearis CLI (JSON-only output; linear is an alias). Do not guess the command surface — the CLI documents itself, and this skill teaches the protocol, not the flags.
Preflight (reactive — branch on the CLI's own output; don't pre-run checks every turn)
- Not installed — if the shell reports command-not-found, tell the user linearis isn't installed and offer
npm install -g linearis. As a no-install fallback, prefix commands withnpx linearis@latest(adds cold-start latency and needs network per call — fallback, not default). Never silentlynpm install -g. - Auth required — any command may fail with this envelope on stderr and exit code 42:
{ "error": "AUTHENTICATION_REQUIRED", "action": "USER_ACTION_REQUIRED", "instruction": "Run 'linearis auth login' …", "exit_code": 42 }. Detect it byexit_code === 42/error === "AUTHENTICATION_REQUIRED"(not paraphrased text) and surface the CLI's owninstruction.linearis auth loginis an interactive browser flow you cannot complete — hand it to the user. - Invalid invocation — an unknown command or option, a wrong argument count, or a command group named without a subcommand fails on stderr with exit code
2:{ "error": "UNKNOWN_COMMAND", "message": "…", "suggestion": "Did you mean read?", "command": "linearis issues", "available_commands": [...], "instruction": "Run 'linearis issues usage' …", "exit_code": 2 }. Recover from the envelope, not by guessing: pick fromavailable_commands, or run theinstruction.erroris one ofUNKNOWN_COMMAND,UNKNOWN_OPTION,MISSING_ARGUMENT,MISSING_REQUIRED_OPTION,MISSING_OPTION_ARGUMENT,TOO_MANY_ARGUMENTS,MISSING_SUBCOMMAND,INVALID_USAGE. A bare group (linearis issues) is a failure, not a request for help. - Updates (advisory, never blocking) — optionally run
linearis version checkonce →{ current, latest, channel, updateAvailable }. IfupdateAvailableis true, mention it and ask the user beforenpm install -g linearis@latest, honoringchannel(don't move anextuser tolatest). npm can hang or rate-limit; on any timeout/error just proceed with the installed version. Read the plain installed version withlinearis version(JSON), not--version.
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.
- yesterday First seen · 52 lines · 111 tokens per session scan A 1189500b1390
linearis is a skill published in the GitHub repository linearis-oss/linearis (248 stars, last pushed 2d ago), licensed MIT. It adds 111 tokens to every session and 1,125 once invoked, about $0.0006 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
linctl
Use linctl as the Linear control surface for agent-safe issue, project, Cycle, ProjectMilestone, organization, user, team, search, release, initiative, customer, notification, attachment, comment, and metadata work. Prefer it over Linear MCP, raw GraphQL, or ad hoc API calls when linctl covers the operation; use…
linear
Linear project management — issues, cycles, and projects via GraphQL API.
stale-sweep
Sweep the googleapis/mcp-toolbox repo for issues and PRs with no real activity in N days (default 60), sort each by whose silence it is (the author's, ours, or nobody's), and draft the nudge or close comment. Use whenever a maintainer asks for a stale sweep, backlog cleanup, or an SLO check, e.g. "stale sweep", "find…
github-issue-triage
Issue triage and lifecycle management agent for ZeroClaw. Use this skill whenever the user wants to: triage open issues, close stale/duplicate/fixed issues, apply labels, run a backlog sweep, enforce the current issue stale policy, or handle a specific issue. Trigger on: 'triage issues', 'issue triage', 'sweep…
backlog-technical-project-manager
Technical project management for Backlog.md workstreams using coordinated sub-agents. Use only when the user explicitly asks Codex to take over one or more existing Backlog.md tasks (for example: "act as TPM", "coordinate these tasks", "delegate to sub-agents"). Orchestrate planning, implementation, and finalization…
goal-conductor
Own a long-horizon goal end to end - decompose it into work items, stand up one top-level session per item, patrol their state on a nudge loop, and decide each next round until the goal is met or a stop condition fires. Use when the user hands over a goal too large for one session ("clear the flaky-test backlog"…