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/elnora-ai/elnora-linear/agents-mdgit clone --depth 1 https://github.com/Elnora-AI/elnora-linearWrote 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/elnora-ai/elnora-linear/agents-md)<a href="https://agentmods.dev/instructions/elnora-ai/elnora-linear/agents-md"><img src="https://agentmods.dev/badge/instructions/elnora-ai/elnora-linear/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 | $0.01631 | $0.01631 |
| Opus 5 | $0.00816 | $0.00816 |
| Sonnet 5 | $0.00326 | $0.00326 |
| Haiku 4.5 | $0.00163 | $0.00163 |
Grade A, and why
elnora-linear 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
Universal guide for any coding agent working with elnora-linear. Read natively by Codex, Cursor, Aider, Continue, Amp, Jules, and Roo. Claude Code reads CLAUDE.md instead — see the Claude Code section below.
What this is
@elnora-ai/linear — one npm package exposing the elnora-linear CLI (full Linear GraphQL coverage) and a config-driven curator. Any agent shells out to the CLI; the JSON output is designed for self-correction from structured errors.
Setup
npm install -g @elnora-ai/linear
export LINEAR_API_KEY=lin_api_... # from https://linear.app/settings/api
elnora-linear sync all # fetch teams, projects, users, workflows
elnora-linear sync verify --output json # confirm what's populated
Config lives at ~/.config/elnora-linear/ (override with LINEAR_REFERENCES_DIR). The key persists to .env mode 0600 after first interactive use.
For a guided multi-step install (verify → key → sync → smoke-test), point your agent at INSTALL_FOR_AGENTS.md.
Dispatch — when to use what
| User intent | Command |
|---|---|
| Create one issue | elnora-linear issues create "Title" --team X --project P --description "md" [--labels L1,L2] [--priority 0-4] [--assignee me] [--state Todo] — --project is required by default (see Pitfalls) |
| Update an issue | elnora-linear issues update ENG-123 [--state ...] [--assignee ...] [--add-comment "..."] |
| Search / list | elnora-linear issues search "terms" --output json |
| My assigned | elnora-linear my-issues --output json |
| Same change to many | elnora-linear bulk --team X [filters] --set-state Y — dry-run by default; --yes to apply |
| Audit stale / wrong-state | elnora-linear cleanup --team X |
| Curator (signals → proposals) | elnora-linear curator-run [--collect-only] [--dry-run] |
| Slack bridge — DM assignees with MEDIUM-tier questions | elnora-linear curator-slack-bridge <tick|post-pending|resolve> [--dry-run] [-v] — needs pip install slack-sdk anthropic + SLACK_BOT_TOKEN; see bridges/slack/README.md |
| Refresh refs | elnora-linear sync all — preserves slack_user_id and user-curated fields across re-syncs |
| What's populated | elnora-linear sync verify --output json |
| Anything else | elnora-linear --help — full GraphQL coverage (comments, views, customers, states, projects, labels, cycles, initiatives, milestones, attachments, status updates, agent sessions, webhooks, …) |
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 · 1,631 tokens per session scan A f0a838de7486
elnora-linear AGENTS.md is an instructions file published in the GitHub repository Elnora-AI/elnora-linear (7 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,631 tokens to every session, about $0.0082 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
lineark CLAUDE.md
Instructions for flipbit03/lineark, covering claude.md — lineark, what is this, workspace layout, key commands and writing online tests: the three pillars.
beads-superpowers CLAUDE.md
Instructions for DollarDill/beads-superpowers, covering beads-superpowers — agent instructions, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.
slopstop CLAUDE.md
Claude Code instructions for iansmith/slopstop, covering slopstop (ticket-plugin), universal project rules, slopstop-specific declarations, tests (per universal §1) and this repo is the tool the other projects' rules run on.
beads-superpowers GEMINI.md
Instructions for DollarDill/beads-superpowers, a project described as: Superpowers & Beads task memory for AI coding agents - supports Claude Code, Codex, OpenCode, Cursor, Gemini CLI, GitHub Copilot CLI, Kimi Code, Antigravity, Factory Droid, and Pi.
beads-superpowers AGENTS.md
Instructions for DollarDill/beads-superpowers, a project described as: Superpowers & Beads task memory for AI coding agents - supports Claude Code, Codex, OpenCode, Cursor, Gemini CLI, GitHub Copilot CLI, Kimi Code, Antigravity, Factory Droid, and Pi.
river-review GEMINI.md
Gemini CLI instructions for s977043/river-review, covering gemini instructions (river-review), 必須チェック, gemini-specific tips, prompt assembly and development tips.