ccmigrate AGENTS.md

Project instructions for ccmigrate, a local command-line tool that moves conversation context between coding tools. They explain its files, commands, export formats, and safety rules.

In plain words
What is it for?
Use them when running tests, inspecting provider conversation stores, listing or exporting project conversations, or creating redacted thread dumps.
Why use it?
They give a coding agent the project context and operating rules needed to work consistently, including safe handling of stored conversations.

Instructions file for CodexOpenCode

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/rajmeet/ccmigrate/agents-md
Clone the repo
git clone --depth 1 https://github.com/Rajmeet/ccmigrate

Made for: Codex, OpenCode.

Per session 1,014 This file is loaded in full into every session.
When invoked 1,014 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.01014 $0.01014
Opus 5 $0.00507 $0.00507
Sonnet 5 $0.00203 $0.00203
Haiku 4.5 $0.00101 $0.00101

Measured 2d ago against content hash d47ce881fa51, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

ccmigrate AGENTS.md scanned grade B 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 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

find /Users/rajmeet/.codex/sessions -name '*<destination_id>*.jsonl' -print
AGENTS.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project

ccmigrate is a local-first MIT CLI for moving agent conversation context across coding tools.

The default product stance is safe export:

  • read provider stores
  • normalize conversations into .ccmigrate/conversations.jsonl
  • export Markdown, JSONL, AGENTS.md, CLAUDE.md, and OPENCODE.md
  • avoid writing provider-owned stores unless the user explicitly asks for native migration

Commands

Run tests:

PYTHONPATH=src python3 -m unittest discover -s tests

List local provider stores:

PYTHONPATH=src python3 -m ccmigrate doctor

List project conversations:

PYTHONPATH=src python3 -m ccmigrate list --project /path-or-name --json

Export latest project conversation safely:

PYTHONPATH=src python3 -m ccmigrate sync --project /path-or-name --limit 1 --store /tmp/ccmigrate-latest
PYTHONPATH=src python3 -m ccmigrate export --store /tmp/ccmigrate-latest --out /tmp/ccmigrate-latest/export

Create a shareable thread dump:

PYTHONPATH=src python3 -m ccmigrate dump --project /path-or-name --limit 1 --out /tmp/thread-dump --zip

Dump behavior:

  • Redaction is enabled by default.
  • Use --id <conversation-id> for exact thread selection.
  • Use --no-redact only when the user explicitly wants private, unredacted sharing.
  • Inspect threads.md before sending the zip to someone.
  • Delete temporary dumps after testing because they contain chat-derived content.

Create a compact handoff when a native migrated session is too large for Codex:

PYTHONPATH=src python3 -m ccmigrate handoff --project /path-or-name --limit 1

For an exact oversized thread:

PYTHONPATH=src python3 -m ccmigrate handoff --id <conversation-id> --project /path/to/project --recent-messages 30

Then start a fresh Codex session with the generated prompt:

cd /path/to/project
codex "$(cat .ccmigrate/handoffs/<timestamp>/codex-prompt.txt)"

Prefer handoff over native migration for very large sessions. Native migration preserves more raw history, but it can make Codex unusable when the transcript is huge. For multi-million-token Claude chats, never try to resume the whole migrated session in Codex. Generate a handoff, start fresh, and search search-shards/ for old details as needed.

Read the full file on GitHub · 139 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 · 139 lines · 1,014 tokens per session scan B d47ce881fa51

Subscribe to this mod's changes

ccmigrate AGENTS.md is an instructions file published in the GitHub repository Rajmeet/ccmigrate (2 stars, last pushed 2mo ago), licensed MIT. It adds 1,014 tokens to every session, about $0.0051 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens