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/smorinlabs/agent2linear/claude-mdgit clone --depth 1 https://github.com/smorinlabs/agent2linearWrote 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/smorinlabs/agent2linear/claude-md)<a href="https://agentmods.dev/instructions/smorinlabs/agent2linear/claude-md"><img src="https://agentmods.dev/badge/instructions/smorinlabs/agent2linear/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 | $0.06030 | $0.06030 |
| Opus 5 | $0.03015 | $0.03015 |
| Sonnet 5 | $0.01206 | $0.01206 |
| Haiku 4.5 | $0.00603 | $0.00603 |
Grade A, and why
agent2linear 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 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.
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 — 471 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agent2linear - Linear CLI Tool
Project Overview
agent2linear is a TypeScript-based command-line tool for creating and managing Linear projects, issues, labels, workflow states, and other entities via the Linear GraphQL API. Designed for AI agents and automation workflows.
CLI Commands:
agent2linear- Full command namea2l- Short alias for convenience
Technology Stack:
- TypeScript (ES2022, ESNext modules)
- Commander.js (CLI framework)
- Ink (React-based terminal UI for interactive modes)
- Linear SDK (@linear/sdk)
- Build: tsup (TypeScript bundler)
- Task runner: turbo
Prerequisites & Setup
Required Environment Variables
export LINEAR_API_KEY=lin_api_xxxxxxxxxxxx
Installation & Build
# For development
npm install
npm run build
# For end users (npm package)
npm install -g agent2linear
Running the CLI
# After build (both commands work identically)
agent2linear --help
a2l --help
# Or via node directly during development
node dist/index.js --help
Development Workflow
Build Commands
npm run build # Production build (tsup)
npm run dev # Watch mode for development
npm run lint # ESLint check
npm run typecheck # TypeScript type checking
npm run format # Prettier formatting
Architecture
- Entry point: src/index.ts → compiles to dist/index.js (with shebang)
- CLI definition: src/cli.ts - all command registration
- Commands: src/commands/<entity>/<action>.ts(x) (.tsx for Ink components)
- Libraries: src/lib/ - shared utilities (aliases, config, linear-client, etc.)
- Types: src/lib/types.ts - TypeScript interfaces for all entities
## Code Intelligence Tooling
This repo enables two Claude Code plugins for code intelligence. They are
declared in the committed `.claude/settings.json` (`enabledPlugins`), so they
apply to everyone who clones the repo:
```json
{
"enabledPlugins": {
"typescript-lsp@claude-plugins-official": true,
"ast-grep@ast-grep-marketplace": true
}
}
Note: enabledPlugins is read at session startup; after editing
.claude/settings.json, start a fresh session for changes to take effect.
Personal/machine-specific overrides belong in .claude/settings.local.json
(gitignored, not shared).
TypeScript LSP (semantic navigation)
Use for questions that require type resolution — "where is X defined / used",
type/JSDoc info, refactor-grade reference analysis, and call hierarchy. Resolves
this repo's ESM .js-extension imports back to their .ts sources via
tsconfig.json.
- Operations:
goToDefinition,findReferences,hover,documentSymbol,workspaceSymbol,goToImplementation,incomingCalls/outgoingCalls. - Plugin:
typescript-lsp@claude-plugins-official.
ast-grep (structural pattern matching)
Use for structural queries that ignore types — "every exported async function
that awaits", "all console.error(...) call sites". Complements the LSP; it
matches on AST shape, not semantics.
- Requires the
ast-grepbinary on PATH (brew install ast-grep). - Match the grammar to the file's role:
--lang tsfor pure-logic.tsfiles,--lang tsxfor Ink/React.tsxcommand files (JSX is a different grammar). - For relational YAML rules (
has/inside), addstopBy: endso the traversal reaches descendants buried in function bodies. - Plugin:
ast-grep@ast-grep-marketplace— docs: https://github.com/ast-grep/claude-skill
Icon Handling (v0.13.2+)
IMPORTANT: Icons are NOT validated client-side.
- Icons are passed directly to Linear API for server-side validation
- The curated icon list (src/lib/icons.ts) is for discovery only, not validation
- Investigation confirmed Linear's API has no endpoint for the standard icon catalog
- The
emojisGraphQL query only returns custom organization emojis (user-uploaded)
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 · 471 lines · 6,030 tokens per session scan A feff7b40893f
agent2linear CLAUDE.md is an instructions file published in the GitHub repository smorinlabs/agent2linear (8 stars, last pushed 19d ago), licensed MIT. It adds 6,030 tokens to every session, about $0.0301 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 2026-08-31.
Other instructions, from other repositories
agents-universe CLAUDE.md
Claude Code instructions for agents-universe/agents-universe, covering agents universe — enterprise ai agent framework, project overview, monorepo layout, development commands and api (from packages/api/).
rn-dev-agent AGENTS.md
AGENTS.md instructions for Lykhoyda/rn-dev-agent, covering repository guide for agents, repository map, editing rules, architecture rules and supported node runtimes.
Formic AGENTS.md
Instructions for rickywo/Formic, covering formic task manager assistant, your capabilities, what you can do, what you cannot do and core behavioral rules.
dirge CLAUDE.md
Claude Code instructions for dirge-code/dirge, covering project instructions for ai agents, beads issue tracker, quick reference, rules and session completion.
Formic CLAUDE.md
Instructions for rickywo/Formic, covering formic task manager assistant, your capabilities, what you can do, what you cannot do and core behavioral rules.
codex-acp-bridge CLAUDE.md
Instructions for normahq/codex-acp-bridge, covering project instructions for ai agents, beads issue tracker, quick reference, rules and session completion.