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/sliamh11/deus/add-linearnpx skills add sliamh11/Deus --skill add-lineargit clone --depth 1 https://github.com/sliamh11/DeusWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/sliamh11/deus/add-linear)<a href="https://agentmods.dev/skills/sliamh11/deus/add-linear"><img src="https://agentmods.dev/badge/skills/sliamh11/deus/add-linear.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00041 | $0.00725 |
| Opus 5 | $0.00020 | $0.00362 |
| Sonnet 5 | $0.00008 | $0.00145 |
| Haiku 4.5 | $0.00004 | $0.00072 |
Grade C, and why
add-linear scanned grade C with 2 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 3d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
grep -q '"linear"' ~/.claude/mcp.json 2>/dev/null && echo "ALREADY_CONFIGURED" || echo "NOT_CONFIGURED" Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
grep -q '"linear"' ~/.claude/mcp.json 2>/dev/null && echo "ALREADY_CONFIGURED" || echo "NOT_CONFIGURED" How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add Linear
This skill adds Linear project management tools to host-side Claude Code sessions via the @tacticlaunch/mcp-linear MCP server. Once installed, you can create/update issues, manage projects and cycles, search your backlog, and track workflow states from conversation.
Phase 1: Pre-flight
Check if already configured
grep -q '"linear"' ~/.claude/mcp.json 2>/dev/null && echo "ALREADY_CONFIGURED" || echo "NOT_CONFIGURED"
grep -q "LINEAR_API_TOKEN" ~/deus/.env 2>/dev/null && echo "TOKEN_SET" || echo "NO_TOKEN"
- If both configured and token set, skip to Phase 3 (Verify).
- If configured but no token, skip to Phase 2 step 1 only.
- Otherwise, continue to Phase 2.
Phase 2: Install and Configure
Step 1: Get API token
Tell the user:
I need a Linear Personal API key. This is a one-time setup:
- Open Linear → Settings → API → Personal API keys
- Click "Create key", give it a label like "Deus"
- Copy the token (format:
lin_api_...) and paste it here
Once the user provides the token:
Add to ~/deus/.env:
grep -q LINEAR_API_TOKEN ~/deus/.env || echo 'LINEAR_API_TOKEN=<pasted-value>' >> ~/deus/.env
Verify it's gitignored:
cd ~/deus && git check-ignore .env || echo "WARNING: .env is NOT gitignored"
Step 2: Configure MCP
Read ~/.claude/mcp.json, merge the new entry into the existing mcpServers object:
"linear": {
"command": "/bin/sh",
"args": ["-c", "set -a && . $HOME/deus/.env && npx -y @tacticlaunch/mcp-linear"]
}
Do not overwrite existing servers.
Step 3: Document
If ~/deus/.env.example does not already have LINEAR_API_TOKEN, add it:
# === Integrations ===
# Linear project management MCP (host-side Claude Code).
# Generate at: Linear Settings → API → Personal API keys
LINEAR_API_TOKEN=
Phase 3: Verify
Tell the user:
Linear MCP is configured. Restart Claude Code (close and reopen the session) for the tools to load.
After restart, test with: "List my Linear teams" — you should see your workspace teams returned via
mcp__linear__linear_getTeams.Available tools include
linear_getIssues,linear_createIssue,linear_updateIssue,linear_searchIssues,linear_getCycles,linear_getProjects, and 130+ more.
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.
- 3d ago First seen · 87 lines · 41 tokens per session scan C 87a68117d359
add-linear is a skill published in the GitHub repository sliamh11/Deus (51 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 725 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (reads agent configuration directories, reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
drive-to-done
Drive a task all the way to a verified done state — write DoD first, verify each item with evidence, stop only at named stop conditions.
tgcli
Read, search, and send Telegram messages via your personal account using the tgcli CLI. Use when the user asks to check their Telegram messages, search Telegram history, send Telegram messages to other people, or monitor Telegram conversations. Do NOT use for normal user chats routed through OpenClaw's Telegram…
agentmail
Email inboxes for AI agents - create addresses, send and receive email, manage threads.
fathom
Query Fathom AI meeting recordings — transcripts, summaries, action items, and searchable meeting history.
limitless
Query Limitless Pendant lifelogs - conversations, meetings, and ambient recordings.
GTD for Datacore
Getting Things Done — task capture, inbox processing, and org-mode management.