agent-sessions CLAUDE.md

agent-sessions CLAUDE.md is an instructions file for Claude Code from jazzyalex/agent-sessions. It costs 319 tokens per session, scanned A, original, MIT.

Shared instructions for coding agents working on the agent-sessions repository. They point agents to the project handover notes and the main agents.md file for authoritative development and interface guidelines.

In plain words
What is it for?
They help agents prepare to edit the repository, follow its shared workflow, apply its interface rules, and handle Git history correctly when changes are explicitly requested.
Why use it?
They prevent agents from relying on stale notes and set boundaries around commits, pushes, authorship, and UI changes.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code; mentions Codex.

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/jazzyalex/agent-sessions/claude-md
Clone the repo
git clone --depth 1 https://github.com/jazzyalex/agent-sessions

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.

agentmods badge for agent-sessions CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jazzyalex/agent-sessions/claude-md.svg)](https://agentmods.dev/instructions/jazzyalex/agent-sessions/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jazzyalex/agent-sessions/claude-md"><img src="https://agentmods.dev/badge/instructions/jazzyalex/agent-sessions/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 319 This file is loaded in full into every session.
When invoked 319 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 $0.00319 $0.00319
Opus 5 $0.00160 $0.00160
Sonnet 5 $0.00064 $0.00064
Haiku 4.5 $0.00032 $0.00032

Measured 6d ago against content hash 493b9bce470b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

agent-sessions 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 6d 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 · 21 lines

What it actually says

CLAUDE Agent Notes

Before starting work, read the newest entry in RepoHandover.md.

This repository uses a shared playbook for all agents (Claude, Codex, Xcode, Cursor, etc.).

Primary source of truth

  • Read agents.md first for project‑wide policies, UX rules, and commit protocols.
  • Treat agents.md as authoritative for UI design language (HIG‑aligned spacing, tokens, and behavior) and development workflow.

Key reminders for Claude Code contributions

  • Follow Conventional Commits and include trailers (Tool, Model, Why when applicable).
  • NEVER commit or push without explicit user request. Only run git commit or git push when user says "commit" or "push".
  • You may advise the user to commit/push, but do not execute these commands proactively.
  • Commit message format: Use clean conventional commits WITHOUT "Generated with Claude Code" footer or "Co-Authored-By: Claude" trailer. Only include Tool/Model/Why trailers.
  • Git authorship: All commits MUST be authored by the repository owner only. Never add Claude as a co-author.
  • When touching UI, use the shared spacing tokens and HIG guidance defined in agents.md.
  • If you add or rename Swift files, use scripts/xcode_add_file.rb to add them to the project (see agents.md → "Adding New Swift Files to Xcode Project").

If anything is unclear, open a short plan in chat and confirm before implementing.

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. 6d ago First seen · 21 lines · 319 tokens per session scan A 493b9bce470b

Subscribe to this mod's changes

agent-sessions CLAUDE.md is an instructions file published in the GitHub repository jazzyalex/agent-sessions (845 stars, last pushed yesterday), licensed MIT. It adds 319 tokens to every session, about $0.0016 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

do-it AGENTS.md

AGENTS.md instructions for tdwhere123/do-it, covering agents.md, file rules, repository, source of truth vs build artifacts and closed-set contracts.

tdwhere123/do-it · 822 tokens

kirby-mcp AGENTS.md

Instructions for bnomei/kirby-mcp, covering repository guidelines, scoped agent guides (keep in sync), project structure & module organization, build, test, and development commands and coding style & naming conventions.

bnomei/kirby-mcp · 860 tokens

GameStudio-CodexKIT AGENTS.md

AGENTS.md instructions for hoatv2211/GameStudio-CodexKIT, covering gamestudio-codexkit operating contract, active sources of truth, primary distribution, repository-local maintenance and evidence.

hoatv2211/GameStudio-CodexKIT · 1,547 tokens

agentic-dev-harness AGENTS.md

Instructions for kohj1018/agentic-dev-harness, covering 프로젝트 지침, 목적, 핵심 행동 규율, 단순성·yagni (구현 시 항상 적용) and claude code plan 모드.

kohj1018/agentic-dev-harness · 1,490 tokens

Hipson AGENTS.md

AGENTS.md instructions for Hipson47/Hipson, covering agents.md instructions for hipson, default behavior, orchestration, subagent prompt quality and coding standards.

Hipson47/Hipson · 744 tokens

open-harness AGENTS.md

Instructions for Open-Harness/open-harness, covering ⚠️ critical: vitest orphaned processes - read this first ⚠️, ⚠️ critical: anthropic sdk testing - read this first ⚠️, ⚠️ critical: no mocks testing philosophy ⚠️, rules and what to use instead.

Open-Harness/open-harness · 3,011 tokens