What is cc-sessions CLAUDE.md?

A set of instructions for cc-sessions, a Claude Code workflow that uses Discussion-Alignment-Implementation-Check (DAIC) to guide coding tasks. It keeps task context between sessions and controls when code changes may be made.

Use it to structure AI-assisted coding, manage task lists with priorities, and coordinate complex work through specialized agents.

It reduces accidental edits by requiring agreement before implementation and limiting work to approved tasks. It also keeps unfinished work organized across sessions.

How GWUDCAP/cc-sessions configures Claude Code

About the project

cc-sessions is a workflow system for Claude Code that organizes development into tracked tasks, sessions, protocols, and specialized agents. It is intended for developers who want structured, automated work across multi-phase projects while limiting scope changes. Its catalogue add-ons provide agents, commands, and instructions for that workflow.

GWUDCAP/cc-sessions · 1,539 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to GWUDCAP/cc-sessions. 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/GWUDCAP/cc-sessions/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/GWUDCAP/cc-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/gwudcap/cc-sessions/claude-md/github.svg)](https://agentmods.dev/instructions/gwudcap/cc-sessions/claude-md)

Your own site

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

Per session 3,761 This file is loaded in full into every session.

When invoked 3,761 The same file — it is already loaded in full.

Security scan A 1 finding. 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	$0.03761	$0.03761
Opus 5.5	$0.01504	$0.01504
Sonnet 5.5	$0.00752	$0.00752
Haiku 4.5	$0.00376	$0.00376

Measured 2mo ago against content hash fa32fc1236b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cc-sessions CLAUDE.md scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Occurs when commands generate stderr output (e.g., curl progress) AND PostToolUse hooks send stderr feedback (exit code 2)

CLAUDE.md · 334 lines

How it starts

The opening of the file, as written. The whole thing — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cc-sessions

A Claude Code workflow framework that enforces structured AI pair programming through Discussion-Alignment-Implementation-Check (DAIC) methodology.

What It Does

cc-sessions transforms Claude Code into a disciplined workflow system where Claude must discuss approaches before writing code, maintains persistent task context across sessions, and provides specialized agents for complex operations. Available in both Python and JavaScript with complete feature parity.

Core Concepts

DAIC Enforcement

Discussion Mode: Default state. Edit/Write/MultiEdit tools blocked until explicit approval
Implementation Mode: Activated by trigger phrases ("yert", "make it so", "run that")
Todo-Based Boundaries: Approved TodoWrite lists define exact implementation scope
Todo Change Detection: Blocks unauthorized todo modifications with detailed diff and required "SHAME RITUAL" response format
Automatic Return: Returns to discussion mode when all todos complete
Configurable: Customize trigger phrases, blocked tools, and enforcement patterns

Task Management

Priority Prefixes: h- (high), m- (medium), l- (low), ?- (investigate)
Two Task Types: File-based for focused work, directory-based for multi-phase projects
Branch Enforcement: Automatic git branch creation and validation (optional, can be disabled)
Persistent Context: Task state preserved across session restarts
Directory Tasks: Multi-subtask workflows on a single feature branch

Sessions State System

Unified state management in sessions/sessions-state.json:

current_task - Active task with frontmatter integration
mode - Current DAIC mode (discussion/implementation)
active_protocol - Currently running protocol (CREATE/START/COMPLETE/COMPACT/None)
todos - Active and stashed todo lists
flags - Context warnings, subagent status
metadata - Runtime state (kickstart progress, update checks)
api - Protocol-specific command permissions

Read the full file on GitHub · 334 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.

2mo ago First seen · 334 lines · 3,761 tokens per session scan A fa32fc1236b6

Subscribe to this mod's changes

cc-sessions CLAUDE.md is an instructions file published in the GitHub repository GWUDCAP/cc-sessions (1,539 stars, last pushed 10mo ago), licensed MIT. It adds 3,761 tokens to every session, about $0.0150 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents Planning

cc-sessions CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
cc-sessions CLAUDE.mdGWUDCAP/cc-sessions	Instructions file	1.5k	10mo ago	MIT	A	3,761	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	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	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

cc-sessions: Instructions file for Claude Code