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 instructions/prime-radiant-inc/streamlinear/claude-mdgit clone --depth 1 https://github.com/prime-radiant-inc/streamlinearWrote 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/instructions/prime-radiant-inc/streamlinear/claude-md)<a href="https://agentmods.dev/instructions/prime-radiant-inc/streamlinear/claude-md"><img src="https://agentmods.dev/badge/instructions/prime-radiant-inc/streamlinear/claude-md.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 5.1 | $0.01081 | $0.01081 |
| Opus 5 | $0.00541 | $0.00541 |
| Sonnet 5 | $0.00216 | $0.00216 |
| Haiku 4.5 | $0.00108 | $0.00108 |
Grade A, and why
streamlinear CLAUDE.md 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 6d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code when working in this repository.
What This Is
streamlinear is a lightweight Linear integration published as the npm package
@primeradianthq/streamlinear.
It ships two runtime binaries from one TypeScript codebase:
streamlinear: the stdio MCP server atmcp/dist/index.js.streamlinear-cli: the local CLI atmcp/dist/cli.js.
The repo also contains .claude-plugin/ for clone-based Claude Code plugin
usage. That plugin surface is intentionally repo-only and is not included in
the npm package.
Most behavior lives in mcp/src/linear-core.ts. The MCP server and CLI should
stay thin shells over that shared module.
Setup
Install dependencies in both workspaces:
npm ci
npm --prefix mcp ci
Common Commands
Run commands from the repository root unless noted otherwise.
npm run build # bundle mcp/dist/index.js and mcp/dist/cli.js
npm run typecheck # TypeScript check for mcp/src
npm run test # node:test coverage under mcp/test
npm run dist:check # verify committed dist artifacts match source
npm run package:check # verify npm metadata and release invariants
npm run pack:verify # pack and install into a temp consumer
npm run check # full local release gate
npm start --prefix mcp # run the MCP server over stdio
To exercise the CLI locally:
LINEAR_API_TOKEN=lin_api_xxx node mcp/dist/cli.js search
node mcp/dist/cli.js --token-cmd "op read 'op://vault/linear/token'" get ABC-123
Build Artifacts
mcp/dist/index.js and mcp/dist/cli.js are checked into git because they are
the files npm executes. Do not hand-edit them. If you change mcp/src/**, run
npm run build and commit any matching mcp/dist/** changes.
Both dist files need a #!/usr/bin/env node shebang. The mcp/package.json
esbuild commands add it with --banner:js.
Package Boundary
The npm package is intentionally small. The root package.json files
allowlist controls the published surface:
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.
- 6d ago First seen · 132 lines · 1,081 tokens per session scan A 3fd7961eda6b
streamlinear CLAUDE.md is an instructions file published in the GitHub repository prime-radiant-inc/streamlinear (89 stars, last pushed 9d ago), licensed MIT. It adds 1,081 tokens to every session, about $0.0054 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 instructions, from other repositories
emdash AGENTS.md
AGENTS.md instructions for generalaction/emdash, covering project overview, repository structure, build & development commands, code style & conventions and architecture notes.
personal-agent-template AGENTS.md
AGENTS.md instructions for vercel-labs/personal-agent-template, covering personal agent template, quick reference, structure, documentation and eve framework.
linear-cli AGENTS.md
AGENTS.md instructions for schpet/linear-cli, covering basics, permissions, error handling, cli flags and tests.
cyrus copilot-instructions.md
Copilot instructions for cyrusagents/cyrus: Note, there is a need to maintain the use of '--print' when running the claude exec commands because that is what makes it non-interactive.
mcp-linear copilot-instructions.md
Instructions for tacticlaunch/mcp-linear, covering mcp linear repository instructions, repository map, how to add or change a tool, validation and project-specific pitfalls.
mcp-linear AGENTS.md
Instructions for tacticlaunch/mcp-linear, covering mcp linear agent notes, primary workflow, repository expectations and validation.