agentmods.dev

lineark CLAUDE.md

A repository instruction file for lineark, an unofficial Rust toolkit for Linear, a project and issue-tracking service. It describes the workspace's libraries, command-line tool, code generator, and development rules.

In plain words
What is it for?
Use it when working on lineark's Rust SDK, command-line tool, procedural macro, or generated API code. It also points to the project's architecture and planning documents.
Why use it?
It gives coding agents the project structure and conventions they need before changing code. This reduces the risk of editing the wrong crate or overlooking required validation.

Instructions file

54 1mo ago A scan 3,334 tokens original MIT
View the source file flipbit03/lineark
Install

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.

agentmods
npx agentmods add instructions/flipbit03/lineark/claude-md
Clone the repo
git clone --depth 1 https://github.com/flipbit03/lineark
Per session 3,334 This file is loaded in full into every session.
When invoked 3,334 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.03334 $0.03334
Opus 5 $0.01667 $0.01667
Sonnet 5 $0.00667 $0.00667
Haiku 4.5 $0.00333 $0.00333

Measured yesterday against content hash 828c51dcb518, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lineark 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 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.

CLAUDE.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — lineark

What is this

lineark is an unofficial Linear (issue tracker) ecosystem for Rust:

  • lineark-sdk (crates/lineark-sdk/) — Async-first Rust SDK for the Linear GraphQL API
  • lineark-derive (crates/lineark-derive/) — Proc macro crate providing #[derive(GraphQLFields)] for type-driven field selection
  • lineark (crates/lineark/) — CLI for humans and LLMs, powered by lineark-sdk
  • lineark-codegen (crates/lineark-codegen/) — Internal tool that reads schema/schema.graphql and generates typed Rust code into crates/lineark-sdk/src/generated/

See docs/MASTERPLAN.md for the full architecture, roadmap, and design decisions (huge file, only read if needed, to keep token consumption down in day-to-day work).

Workspace layout

Cargo.toml              # workspace root
crates/
  lineark-sdk/          # library (published to crates.io)
  lineark-derive/       # proc macro for #[derive(GraphQLFields)]
  lineark/              # CLI binary (published to crates.io + binary releases)
  lineark-codegen/      # codegen tool (not published)
schema/
  schema.graphql        # Linear's GraphQL schema (checked in, fetched from API)
  operations.toml       # allowlist of which queries/mutations to generate
docs/
  MASTERPLAN.md         # full project plan and roadmap

Key commands

rustup update stable                     # sync local toolchain with CI (do this before developing)
cargo run -p lineark-codegen             # regenerate SDK types from schema
cargo run -p lineark -- <args>           # run the CLI
make check                               # lint + doc + build (no tests)
make test                                # offline tests (unit + integration, fast, no API token)
make test-online                         # online tests (live API, serial, needs token)

make check && make test is the canonical local pre-push check. Add make test-online when you have a test API token and need full coverage.

Online tests must run serially. They hit the live Linear API, which has plan-level limits (e.g. max teams). Running them in parallel causes spurious failures from resource exhaustion. make test-online handles this automatically.

Read the full file on GitHub · 177 lines

Changes

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.

  1. yesterday First seen · 177 lines · 3,334 tokens per session scan A 828c51dcb518

Subscribe to this mod's changes

lineark CLAUDE.md is an instructions file published in the GitHub repository flipbit03/lineark (54 stars, last pushed 1mo ago), licensed MIT. It adds 3,334 tokens to every session, about $0.0167 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.

Backend and APIsProject managementTestingagentscliissue-trackerlinearsdk
Related

Other instructions, from other repositories

elnora-linear AGENTS.md

Instructions for Elnora-AI/elnora-linear, covering agents.md, what this is, setup, dispatch — when to use what and pitfalls.

Elnora-AI/elnora-linear · 1,631 tokens

skills copilot-instructions.md

Copilot instructions for microsoft/skills, covering copilot instructions for agent skills, project overview, ⚠️ fresh information first, core principles and 1. think before coding.

microsoft/skills · 2,575 tokens

beads AGENTS.md

AGENTS.md instructions for gastownhall/beads, covering agent instructions, key sections, project scope, pr safety for agents and visual design anti-patterns.

gastownhall/beads · 2,901 tokens

orbit CLAUDE.md

Instructions for Noveum/orbit, covering orbit, hard rules, bun is the toolchain, not the runtime, layout and commands.

Noveum/orbit · 3,943 tokens

orbit AGENTS.md

Instructions for Noveum/orbit, covering agent instructions, the short version, rules that will fail the build and before you report a task finished.

Noveum/orbit · 630 tokens

blz AGENTS.md

Instructions for outfitter-dev/blz, covering blz repository instructions for ai agents, important, working memory, use blz and 🚀 quick start for agents.

outfitter-dev/blz · 1,615 tokens