What is backpass CLAUDE.md?

Repository instructions for backpass, a project whose description says its behaviour is trained with gradient descent rather than written through AGENTS.md files. Gradient descent is a method used to adjust machine-learning models from examples.

Understanding and modifying the backpass project according to its repository instructions.

They clarify the project’s unusual development approach and provide the expected guidance for working in its repository.

How kunchenguid/backpass configures Claude Code

About the project

backpass is a local tool that reviews coding-agent session transcripts and proposes evidence-backed changes to an agent's memory files, such as AGENTS.md and project skills. Developers use it to improve agent instructions from past work while keeping a person responsible for approving and applying edits. The catalogue entries are instructions for using backpass.

kunchenguid/backpass · 1,471 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to kunchenguid/backpass. 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/kunchenguid/backpass/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/kunchenguid/backpass

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/kunchenguid/backpass/claude-md/github.svg)](https://agentmods.dev/instructions/kunchenguid/backpass/claude-md)

Your own site

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

Per session 25 This file is loaded in full into every session.

When invoked 25 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 100% copy Near-identical to another mod 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	$0.00025	$0.00025
Opus 5.5	$0.00010	$0.00010
Sonnet 5.5	$0.00005	$0.00005
Haiku 4.5	$0.00003	$0.00003

Measured 2mo ago against content hash 71e896252aba, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

backpass 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 2mo 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.

Origin

This is a copy

100% identical to no-mistakes CLAUDE.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 3 lines

What it actually says

@AGENTS.md

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.

2mo ago First seen · 3 lines · 25 tokens per session scan A 71e896252aba

Subscribe to this mod's changes

backpass CLAUDE.md is an instructions file published in the GitHub repository kunchenguid/backpass (1,471 stars, last pushed 4d ago), licensed MIT. It adds 25 tokens to every session, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to no-mistakes CLAUDE.md, differing in 0 lines, and is treated as a copy.

backpass CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
backpass CLAUDE.mdkunchenguid/backpass	Instructions file	1.5k	4d ago	MIT	A	25	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
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

backpass: Instructions file for Claude Code