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/consensys/doc.linea/agents-mdgit clone --depth 1 https://github.com/Consensys/doc.lineaWhat 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 | $0.00879 | $0.00879 |
| Opus 5 | $0.00439 | $0.00439 |
| Sonnet 5 | $0.00176 | $0.00176 |
| Haiku 4.5 | $0.00088 | $0.00088 |
Grade A, and why
doc.linea 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 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agent Instructions
Rules for AI coding agents (Claude Code, GitHub Copilot, Cursor, Codex, etc.) working on
this Docusaurus v3 documentation site, docs.linea.build.
Repository areas
| Tab | Directory | Documents |
|---|---|---|
| Linea Mainnet | docs/network |
Linea Mainnet |
| Lineth Stack | docs/stack |
Lineth (the operator stack) |
| Protocol | docs/protocol |
Lineth (the protocol) |
| Reference | docs/api |
Linea and Lineth |
| Changelog | docs/changelog |
Linea and Lineth |
See README.mdx for full tab descriptions, audiences, and the src/
component/theme layout.
Critical rules
- Do not invent protocol or API behavior. Never state as fact any parameter, return
value, or behavior you haven't verified against source code, a spec, or another
authoritative reference. If uncertain, mark it
[VERIFY](seeeditorial-voice.mdc). - Use Linea and Lineth precisely. They're related but distinct terms. Check
/protocol/linea-vs-linethbefore asserting which one applies to a claim, and don't guess from memory. See.cursor/rules/terminology.mdc. - Never hardcode brand colors, spacing, or radii in
src/. Use thevar(--linea-*)design tokens insrc/css/tokens.css. See.cursor/rules/css-styling.mdc. - Verify before requesting review. Preview locally with
npm run start, and confirmnpm run buildsucceeds. - Pass CI. PRs run ESLint/Stylelint, TypeScript, Vale spelling/style, and link checking. Fix warnings before requesting review; see Quality checks before pushing.
AI guidance
Detailed rules live in .cursor/rules/ and apply automatically in Cursor when editing a
file matching their globs. Other agents should read the relevant file directly before
editing matching content:
| Rule file | Applies to | Covers |
|---|---|---|
content-structure.mdc |
docs/**/*.{md,mdx} |
Tab/audience/tone, page structure |
editorial-voice.mdc |
docs/**/*.{md,mdx} |
Voice, heading style, [VERIFY] markers |
terminology.mdc |
docs/**/*.{md,mdx} |
Casing, Linea/Lineth naming, component capitalization |
markdown-formatting.mdc |
docs/**/*.{md,mdx} |
Frontmatter, links, line wrapping, images |
contributor-workflow.mdc |
repo-wide | Issue-first workflow, redirects, PR hygiene |
css-styling.mdc |
src/**/*.{css,tsx,jsx,ts,js} |
CSS architecture, design tokens, forbidden patterns |
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 · 65 lines · 879 tokens per session scan A 9eb057dfb62e
doc.linea AGENTS.md is an instructions file published in the GitHub repository Consensys/doc.linea (474 stars, last pushed 6d ago), licensed Apache-2.0. It adds 879 tokens to every session, about $0.0044 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
lineth-monorepo AGENTS.md
Instructions for LFDT-Lineth/lineth-monorepo, covering agents.md, documentation precedence, agent entry points, local agent workflows and discoverability index.
lineth-monorepo CLAUDE.md
Instructions for LFDT-Lineth/lineth-monorepo, covering claude.md, purpose, precedence, discoverability and note.
lineth-monorepo copilot-instructions.md
Instructions for LFDT-Lineth/lineth-monorepo, covering github copilot instructions, purpose, precedence, discoverability and note.
liam AGENTS.md
Instructions for liam-hq/liam, covering repository guidelines, project structure & modules, build, test, and development, coding style & naming and testing guidelines.
tevm CLAUDE.md
Claude Code instructions for evmts/tevm, covering tevm monorepo commands and style guide, project overview, forking implementation, json-rpc support and commands.
core copilot-instructions.md
Instructions for asdecided/core: These decisions are already accepted. Do not re-open or contradict them; ask the AsDecided MCP tools (getartifact, searchartifacts) for the full text before proposing a change that touches one.