A cross-agent memory and file workspace that records coding-agent sessions and makes their context available across tools such as Claude Code, Codex, OpenCode, Gemini CLI, and Cursor.

Use it to continue interrupted tasks, search past sessions, retrieve relevant project context, inspect handoffs, and share important artifacts between agents.

It helps you resume earlier work without relying on memory or manually reconstructing what another agent did. It can also find earlier sessions and save files for other agents to use.

agentdrive — Skill for Claude Code by Rakesh1002/agentdrive-mcp

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.

Any agent

npx skills add Rakesh1002/agentdrive-mcp --skill agentdrive

Clone the repo

git clone --depth 1 https://github.com/Rakesh1002/agentdrive-mcp

Made for: Claude Code.

Or install agentdrive, the plugin that ships this one along with the rest of its 1 skill, 3 commands, 4 hooks, 1 MCP server.

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/skills/rakesh1002/agentdrive-mcp/agentdrive/github.svg)](https://agentmods.dev/skills/rakesh1002/agentdrive-mcp/agentdrive)

Your own site

<a href="https://agentmods.dev/skills/rakesh1002/agentdrive-mcp/agentdrive"><img src="https://agentmods.dev/badge/skills/rakesh1002/agentdrive-mcp/agentdrive/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/skills/rakesh1002/agentdrive-mcp/agentdrive"><img src="https://agentmods.dev/badge/skills/rakesh1002/agentdrive-mcp/agentdrive.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 502 The whole file, excluding the scripts and references it only reads on demand.

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	$0.00067	$0.00502
Opus 5.5	$0.00027	$0.00201
Sonnet 5.5	$0.00013	$0.00100
Haiku 4.5	$0.00007	$0.00050

Measured 6d ago against content hash 312fb5d2f32b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agentdrive 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.

plugins/agentdrive/skills/agentdrive/SKILL.md · 55 lines

What it actually says

AgentDrive

AgentDrive captures the user's agent sessions in the background and makes any of them resumable from any harness. Prefer the drive_* MCP tools; fall back to the adrive CLI when they are not available.

Sessions

"Continue where I left off", "pick up the Codex session", "what was I doing?": call drive_resume (optionally with session_id or platform). Summarize the handoff in a few bullets, check the files it mentions on disk, then continue the work.
"What sessions do I have?", "what did Cursor do today?": call drive_sessions (filters: project, platform, limit).

Both default to the current project.

Context and search

Starting a non-trivial task: call drive_context with a one-line summary of the task to get relevant artifacts and runs from earlier work.
Looking for something specific: call drive_search.

When citing a result, say why it surfaced (attribution.reasons) and mention the last_run task when present.

Saving work

After producing a file worth sharing with the user's other agents, call drive_write. Transcripts and files git doesn't track are already captured automatically when the user has capture on, so don't re-upload them.

CLI fallback

adrive resume [session-id]   # print a session handoff
adrive resume --list         # list recent sessions
adrive context "<task>"      # relevant artifacts for a task
adrive search "<query>"      # semantic search
adrive push <file>           # save an artifact

If adrive says the user is not logged in, ask them to run adrive init (or /agentdrive:login in Claude Code). Never guess credentials.

Privacy

Respect adrive privacy. With "Private workspace" on, content is encrypted on the device and the server stores only ciphertext.

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.

6d ago Changed · +4 tokens per session 312fb5d2f32b
17d ago First seen · 55 lines · 63 tokens per session scan A c12941d2e3fe

Subscribe to this mod's changes

agentdrive is a skill published in the GitHub repository Rakesh1002/agentdrive-mcp (1 stars, last pushed 6d ago), licensed Apache-2.0. It adds 67 tokens to every session and 502 once invoked, about $0.0003 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 2026-10-22.

Building agents Memory and context

agentdrive next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agentdriveRakesh1002/agentdrive-mcp	Skill	1	6d ago	Apache-2.0	A	67	Claude Code
knowledge-ingestopenclaw/openclaw	Skill	394k	today	MIT	A	80	Claude Code, Codex
mem0-oss-to-platformmem0ai/mem0	Skill	69k	yesterday	Apache-2.0	A	217	Claude Code, Codex
forgetasgeirtj/system_prompts_leaks	Skill	71k	today	CC0-1.0	A	0	Claude Code, Codex
Cortexdanielmiessler/LifeOS	Skill	20k	2d ago	MIT	A	184	Claude Code
memoryopensquilla/opensquilla	Skill	7.1k	yesterday	Apache-2.0	A	44	Claude Code, Codex
ha-data-storesshiwenwen/hope-agent	Skill	1.9k	today	MIT	A	115	Claude Code, Codex