Elliot CLAUDE.md

Elliot CLAUDE.md is an instructions file for coding agents from EliBarak12/Elliot. It costs 1,136 tokens per session, scanned A, original, MIT.

A set of project instructions for Elliot, a platform that helps product engineers make APIs and databases usable by AI agents.

In plain words
What is it for?
Use it when contributing to Elliot to understand its mission and run the specified Python and JavaScript checks before every push.
Why use it?
It defines rules for clear tool descriptions, compact results, useful errors, session visibility, and required checks before code is pushed.

Instructions file

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/elibarak12/elliot/claude-md
Clone the repo
git clone --depth 1 https://github.com/EliBarak12/Elliot

Wrote 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.

agentmods badge for Elliot CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/elibarak12/elliot/claude-md.svg)](https://agentmods.dev/instructions/elibarak12/elliot/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/elibarak12/elliot/claude-md"><img src="https://agentmods.dev/badge/instructions/elibarak12/elliot/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,136 This file is loaded in full into every session.
When invoked 1,136 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 5.1 $0.01136 $0.01136
Opus 5 $0.00568 $0.00568
Sonnet 5 $0.00227 $0.00227
Haiku 4.5 $0.00114 $0.00114

Measured 5d ago against content hash 89631d2b1d06, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

Elliot 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 5d 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.

CLAUDE.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Elliot — CLAUDE.md

Project Mission

Elliot is a platform that turns existing products into agentic products.

The target user is a product engineer who has a working API or database today and wants AI agents to interact with it natively — with minimum tokens, clean error recovery, and full observability. Elliot provides the tools to design, validate, deploy, and observe agent-ready tool sets built around any API or DB.

The five principles that drive every technical decision:

  1. Tool descriptions are contracts — verb-first, unambiguous, typed
  2. Results are sized for context windows — not raw table dumps
  3. Errors are actionable — agents must know what to do next
  4. Every agent session is observable — token cost, latency, errors, all visible
  5. The platform itself is agentic — agents can build connectors through Elliot

Before Every Push — Mandatory Checks

uv run ruff check .
uv run ruff format --check .
uv run mypy packages/core/src packages/mcp-plugin/src packages/connector-runtime/src
uv run pytest --tb=short
pnpm --filter @elliot/studio run typecheck
pnpm --filter @elliot/studio test --run

All six must pass. Fix the issue, re-run from the top, then push.


Branch Strategy

main
└── epic/01-monorepo-setup
    ├── task/001-root-workspace
    ├── task/002-python-tooling
    └── task/004-package-stubs
└── epic/02-core-library
    ├── task/005-core-type-definitions
    └── ...

Rules

  1. Epic branch from main. Task branch from its epic branch.
  2. Merge task → epic (no-ff). Merge epic → main only when all tasks pass.
  3. Never commit directly to main.
  4. Rename task file to complete-NNN-name.md on epic branch after merge.

Task Completion Protocol

  1. Read the task file in full before writing code.
  2. Implement only what the task specifies — no extra features.
  3. Write unit tests as part of the same commit.
  4. Run the full check suite (above). Fix failures.
  5. Push task branch. Merge into epic.
  6. Rename task file: 001-root-workspace.mdcomplete-001-root-workspace.md.
  7. Commit the rename on the epic branch.

Read the full file on GitHub · 140 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. 5d ago First seen · 140 lines · 1,136 tokens per session scan A 89631d2b1d06

Subscribe to this mod's changes

Elliot CLAUDE.md is an instructions file published in the GitHub repository EliBarak12/Elliot (11 stars, last pushed 5d ago), licensed MIT. It adds 1,136 tokens to every session, about $0.0057 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.

Related

Other instructions, from other repositories

agent-rules testing.instructions.md

Instructions for lirantal/agent-rules, covering testing guidelines for node.js applications, general testing principles, guiding principles, descriptive test naming (three-part structure) and structure tests by the aaa pattern.

lirantal/agent-rules · 6,713 tokens

turbo-flow CLAUDE.md

Claude Code instructions for marcuspat/turbo-flow, covering claude.md — turbo flow, what this repo is, key files and conventions.

marcuspat/turbo-flow · 158 tokens

agent-rules child-process.instructions.md

Instructions for lirantal/agent-rules, covering system processes secure coding guidelines, your mission and spawning system processes.

lirantal/agent-rules · 196 tokens

bdb-dev-optimized-agent-skills CLAUDE.md

Claude Code instructions for hybridlabor-api/bdb-dev-optimized-agent-skills, covering bdb agent skills — global instructions, docs & pipeline, how many agents, safety gate — mechanically enforced, not advisory and non-negotiable.

hybridlabor-api/bdb-dev-optimized-agent-skills · 700 tokens

skill-bill CLAUDE.md

Claude Code instructions for oila-gmbh/skill-bill, a project described as: SkillBill packages your engineering judgment into governed skills, then uses a durable Kotlin runtime to ensure agents actually execute that process consistently, resumably, and with bounded context.

oila-gmbh/skill-bill · 3 tokens

orc AGENTS.md

AGENTS.md instructions for spencermarx/orc, covering openspec instructions, landing the plane (session completion) and open code review instructions.

spencermarx/orc · 552 tokens