Agent Beacon is a local-first memory layer that records AI coding-agent sessions and turns useful workflows, corrections, and debugging patterns into knowledge that other agents can reuse. Developers use it across Claude Code, Cursor, Codex, OpenCode, and other agent harnesses so lessons and repository conventions persist between sessions. The catalogue entries provide instructions and a skill for working with Beacon's shared agent memory.
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.
npx skills add Asymptote-Labs/agent-beacon --skill beacon-session-handoffgit clone --depth 1 https://github.com/Asymptote-Labs/agent-beaconWrote 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.
[](https://agentmods.dev/skills/asymptote-labs/agent-beacon/beacon-session-handoff)<a href="https://agentmods.dev/skills/asymptote-labs/agent-beacon/beacon-session-handoff"><img src="https://agentmods.dev/badge/skills/asymptote-labs/agent-beacon/beacon-session-handoff/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.
<a href="https://agentmods.dev/skills/asymptote-labs/agent-beacon/beacon-session-handoff"><img src="https://agentmods.dev/badge/skills/asymptote-labs/agent-beacon/beacon-session-handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00057 | $0.00414 |
| Opus 5.5 | $0.00023 | $0.00166 |
| Sonnet 5.5 | $0.00011 | $0.00083 |
| Haiku 4.5 | $0.00006 | $0.00041 |
Grade A, and why
beacon-session-handoff 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 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.
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.
What it actually says
Beacon session handoff
Use Beacon to transfer local session context without copying the conversation into a command line. The destination starts independently in a new terminal or a resumable tmux session.
Workflow
-
If the user did not provide a session ID, inspect sessions with:
beacon handoff list --hereKeep the default directory scope unless the user asks to search elsewhere. If more than one plausible session is returned, ask the user which one to continue.
-
Resolve the destination from the user's request. Do not invent a destination runtime.
-
After identifying an unambiguous session and destination, launch it with:
beacon handoff resume <session-id> --agent <runtime> --launch auto --yes--launch autoopens another terminal in the calling cmux workspace or a new terminal on macOS, Windows, or a Linux desktop. In SSH and headless Linux environments it creates a detached tmux session and prints the attach command. If automatic launch cannot find a safe terminal surface, report the error and use:beacon handoff resume <session-id> --agent <runtime> --print -
Report the returned terminal launcher or tmux attach command. Do not claim success when the command returns an error.
Do not run the destination agent directly inside the current harness's non-TTY command tool. Do not add flags or environment variables that disable the destination runtime's approval prompts.
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.
- 2d ago First seen · 46 lines · 57 tokens per session scan A e75560137bb1
beacon-session-handoff is a skill published in the GitHub repository Asymptote-Labs/agent-beacon (2,808 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 414 once invoked, about $0.0002 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 2026-10-24.
Other skills, from other repositories
create-task
Create and verify recurring or one-shot reminders, scripts, agent jobs, reports, and interactive skill launches.
task
Create, edit, and manage scheduled tasks. Tasks live at /.abtars/tasks/ — each task is a directory.
gmail
Read and manage Gmail via gws-cli.
gdrive-backup
Weekly backup of config + encrypted memory to Google Drive.
todo
Manage a persistent todo list.
changelog
Generates a changelog entry from recent commits.