What is TezAtlas CLAUDE.md?

Project instructions for TezAtlas, a workflow for producing academic documents with an AI coding agent. They cover starting or recovering a project, asking questions, using sources, and reviewing academic work.

Use them to manage thesis, article, and other academic projects, including source reading, notes, arguments, and peer review.

They help the agent resume work after lost context and avoid writing without local sources or inventing citations.

How tialkan/TezAtlas configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to tialkan/TezAtlas. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/tialkan/TezAtlas/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/tialkan/TezAtlas

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/tialkan/tezatlas/claude-md/github.svg)](https://agentmods.dev/instructions/tialkan/tezatlas/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/tialkan/tezatlas/claude-md"><img src="https://agentmods.dev/badge/instructions/tialkan/tezatlas/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/tialkan/tezatlas/claude-md"><img src="https://agentmods.dev/badge/instructions/tialkan/tezatlas/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,427 This file is loaded in full into every session.

When invoked 1,427 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01427	$0.01427
Opus 5.5	$0.00571	$0.00571
Sonnet 5.5	$0.00285	$0.00285
Haiku 4.5	$0.00143	$0.00143

Measured today against content hash ef09533ae9c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

TezAtlas 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 today.

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.

TezAtlas — CLAUDE.md (Auto-loaded Context)

This file is read by Claude at session start.

Project

TezAtlas is an Agentic AI Workflow Framework for producing any academic output. Run /tezatlas to begin a new project or resume an existing one.

Session Recovery

If context is lost, follow these steps:

Read skills/core/onboarding.md → determine document type and language
Read STATUS.md (if it exists) → current phase and progress
Read READING_REPORT.md (if it exists) → source reading progress
Check notes/ folder → completed source notes
Run /tezatlas to re-initialize if needed

Question Protocol (always active)

Decide what you safely can. Before any question, look for the answer in the user's words and the project files. When you must ask, give 2-4 concrete options, the recommended one first with its reason, and "write your own" last. "You decide" selects the recommendation. Full protocol: skills/ux/question-protocol.md.

Iron Rules (always active)

No writing without source in local /sources/ folder
Snowball sampling mandatory (follow footnotes)
AI downloads sources first before asking user
No fabricated citations — ever
AI Peer Review OR advisor/supervisor checkpoints before phase transitions
Git commit mandatory after every session
No progress without action — escalate blockers immediately
Defense armor at reading phase exit (strongest support + counter per argument)
Deferred source pool reviewed before writing phase

Operating Modes

Research Copilot / Guided Writing (default): AI generates A/B draft options per section. User selects, merges, or redirects. Academic Writing Note explains reasoning. Available to all users. Thought Partner: AI guides, questions, checks. User writes every word. Switch with /mode assistant.

Hard rule: AI NEVER generates core thesis, arguments, data interpretation, or conclusions — in either mode.

AI Peer Review active at every phase gate for all users (see reviewer-mode.md).

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.

today First seen · 140 lines · 1,427 tokens per session scan A ef09533ae9c6

Subscribe to this mod's changes

TezAtlas CLAUDE.md is an instructions file published in the GitHub repository tialkan/TezAtlas (33 stars, last pushed 12d ago), licensed MIT. It adds 1,427 tokens to every session, about $0.0057 per session on Opus 5.5. 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 2026-11-07.

Research Writing and docs

TezAtlas CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
TezAtlas CLAUDE.mdtialkan/TezAtlas	Instructions file	33	12d ago	MIT	A	1,427	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	3d ago	MIT	A	4,313	Codex, OpenCode

TezAtlas: Instructions file for Claude Code