ateles CLAUDE.md

ateles CLAUDE.md is an instructions file for coding agents from markmhendrickson/ateles. It costs 9,393 tokens per session, scanned A, original, MIT.

A set of project instructions for Claude Code covering plan maintenance, session continuity, and working rules.

In plain words
What is it for?
It is for controlling how Claude Code maintains plans, handles session state, and follows repository-specific procedures.
Why use it?
It helps an AI coding assistant keep work attached to the right project plan and preserve important instructions between sessions.

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/markmhendrickson/ateles/claude-md
Clone the repo
git clone --depth 1 https://github.com/markmhendrickson/ateles

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 ateles CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/markmhendrickson/ateles/claude-md.svg)](https://agentmods.dev/instructions/markmhendrickson/ateles/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/markmhendrickson/ateles/claude-md"><img src="https://agentmods.dev/badge/instructions/markmhendrickson/ateles/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 9,393 This file is loaded in full into every session.
When invoked 9,393 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 $0.09393 $0.09393
Opus 5 $0.04696 $0.04696
Sonnet 5 $0.01879 $0.01879
Haiku 4.5 $0.00939 $0.00939

Measured 2d ago against content hash fb4bfd12ed20, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

ateles 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 2d 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 · 224 lines

How it starts

The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ateles — Claude Code Project Instructions

Plan and task maintenance (automatic)

Each session maintains the Neotoma plan entity that matches its own workstream — never a fixed, hardcoded plan. The swarm-architecture plan ent_99ace4dd6673aa36ed08b1fe ("Ateles Agent Swarm Architecture") is the plan for swarm-architecture work only. Unrelated workstreams (tax prep, Neotoma release engineering, website, cloud hosting, etc.) each have their own plan and MUST NOT write into the swarm plan. Writing one workstream's decisions/todos into another's plan is the collision that corrupted this plan in June 2026.

Select the bound plan once per session, as soon as the workstream is clear:

  1. Resolve the matching plan: mcp__mcpsrv_neotoma__retrieve_entities with entity_type: plan and a search for the workstream; pick the closest match.
  2. If no existing plan fits, create one (/update-plan skill) and bind to it.
  3. Maintain only that bound plan for the rest of the session.

Apply these rules on every turn, without being asked — to the bound plan:

  • Before correcting decisions or todos, RE-READ the current field and MERGE. correct replaces the entire field, so add or update only the keys/items you authored and preserve every entry already present. NEVER rebuild a field from a stale in-memory copy — that silently deletes other sessions' entries. If the field changed since you last read it, re-read and re-merge before writing.
  • When a todo item is completed — correct its status to "done" in todos, with relevant entity IDs, file paths, or PR numbers in a notes field.
  • Never mark a task or todo done while citing a commit, branch, file, or PR that does not resolve. Verify the artifact exists first (git cat-file/ls-remote, GitHub). Unverifiable completion claims are the second failure mode that corrupted this plan in June 2026.
  • When a decision is settled — add or correct one entry in the decisions map. One sentence, snake_case key.
  • When blockers change (something unblocked, something newly blocked) — correct next_steps to reflect the current state.
  • When a new actionable task is identified — create a task entity and link it PART_OF the bound plan. Use the update-tasks skill for field values and priority mapping.
  • When a daemon, entity, or file is renamed — correct any stale references in body, decisions, and todos in the same turn the rename happens.

Read the full file on GitHub · 224 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. 2d ago First seen · 224 lines · 9,393 tokens per session scan A fb4bfd12ed20

Subscribe to this mod's changes

ateles CLAUDE.md is an instructions file published in the GitHub repository markmhendrickson/ateles (6 stars, last pushed yesterday), licensed MIT. It adds 9,393 tokens to every session, about $0.0470 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 2026-09-03.