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/agents-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/agents-md)<a href="https://agentmods.dev/instructions/prime-radiant-inc/streamlinear/agents-md"><img src="https://agentmods.dev/badge/instructions/prime-radiant-inc/streamlinear/agents-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 | $0.00635 | $0.00635 |
| Opus 5 | $0.00318 | $0.00318 |
| Sonnet 5 | $0.00127 | $0.00127 |
| Haiku 4.5 | $0.00064 | $0.00064 |
Grade A, and why
streamlinear AGENTS.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 4d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
These instructions apply to this repository.
Project
streamlinear publishes @primeradianthq/streamlinear, a small Linear MCP/CLI
package for Claude Code and other MCP consumers.
The package exposes:
streamlinear: stdio MCP server, backed bymcp/dist/index.js.streamlinear-cli: local command-line interface, backed bymcp/dist/cli.js.
Source lives under mcp/src. The shared behavior is in
mcp/src/linear-core.ts; keep the MCP server and CLI entry points thin.
Setup
Install both dependency trees before verification:
npm ci
npm --prefix mcp ci
Verification
Use the smallest relevant check while developing, and run the full gate before claiming release readiness.
npm run build
npm run typecheck
npm run test
npm run dist:check
npm run package:check
npm run pack:verify
npm run check
npm run check is the full local release gate. It builds, typechecks, tests,
checks committed dist artifacts, validates package metadata, runs production
dependency audits, and verifies the packed tarball in a temp consumer.
Build Artifacts
mcp/dist/index.js and mcp/dist/cli.js are committed on purpose because npm
executes those files directly. Do not hand-edit dist. If mcp/src/** changes,
run npm run build and commit any resulting dist changes.
Package Boundary
The npm package surface is the root package.json files allowlist. Keep
repo-only agent/plugin/development files out of npm unless Drew explicitly asks
to publish them.
Currently clone/dev-only:
AGENTS.mdCLAUDE.md.claude-plugin/**.github/**scripts/**mcp/src/**mcp/test/**
Do not add npm lifecycle hooks such as prepare, postinstall, or
prepublishOnly. Consumers should not need a build step during install.
Development Hooks
Optional clone hooks use Lefthook and are installed explicitly with:
npm run hooks:install
Keep hooks clone/dev-only. They should check or rebuild local artifacts for contributors; they should not mutate package consumers.
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.
- 4d ago First seen · 97 lines · 635 tokens per session scan A cdd754c554bc
streamlinear AGENTS.md is an instructions file published in the GitHub repository prime-radiant-inc/streamlinear (89 stars, last pushed 7d ago), licensed MIT. It adds 635 tokens to every session, about $0.0032 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.
linearis AGENTS.md
AGENTS.md instructions for linearis-oss/linearis, covering agents.md, identity, audience, quick commands and commit rules.
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.
macro CLAUDE.md
Claude Code instructions for macro-inc/macro, covering claude.md, architecture overview, key services, data storage and macrodb schema changes.