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-trace-sharegit 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-trace-share)<a href="https://agentmods.dev/skills/asymptote-labs/agent-beacon/beacon-trace-share"><img src="https://agentmods.dev/badge/skills/asymptote-labs/agent-beacon/beacon-trace-share/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-trace-share"><img src="https://agentmods.dev/badge/skills/asymptote-labs/agent-beacon/beacon-trace-share.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 | $0.00085 | $0.01055 |
| Opus 5.5 | $0.00034 | $0.00422 |
| Sonnet 5.5 | $0.00017 | $0.00211 |
| Haiku 4.5 | $0.00009 | $0.00105 |
Grade A, and why
beacon-trace-share 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Beacon trace share
beacon share publishes one agent session as a shared trace on beacon.sh: the prompts, the
agent's answers and reasoning, and every tool call with its result, after Beacon's secret
redaction and with local paths made relative. It prints a link the user can send to anyone they
choose.
Sharing uploads the conversation. Only share when the user asked for it, and never change the visibility to public without asking.
Step 1: check that Beacon is available
beacon version
If beacon is not found, tell the user that sharing needs the Beacon CLI, point them to
https://docs.beacon.sh/get-started/overview, and stop. Do not install it yourself.
Step 2: share this session
Run this from the session's working directory, naming your own runtime with --harness:
beacon share --current --harness <runtime> --json
| You are | <runtime> |
|---|---|
| Claude Code | claude_code |
| Codex CLI | codex |
| Cursor | cursor |
| OpenCode | opencode |
| Gemini CLI | gemini |
| GitHub Copilot CLI | copilot |
| Another runtime | its name from beacon share --help, or auto |
--current finds the session this command runs inside: from BEACON_SESSION_ID when the
runtime exports it, otherwise from the session Beacon's hooks last saw in this directory,
otherwise the most recent session here. --harness keeps it from picking another runtime's
session in the same directory.
The default visibility is direct: anyone with the link can open it, and it is not listed anywhere. Keep that unless the user asked for something else:
- private (only the user, when signed in): add
--visibility private. - public (listed in Discover for anyone to find): first ask the user to confirm that the whole
session may be public. Only after they say yes, add
--visibility public --yes.
To see exactly what would be uploaded without uploading anything, run the same command with
--print in place of --json.
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.
- 4d ago First seen · 103 lines · 85 tokens per session scan A 5fcc6f320d01
beacon-trace-share is a skill published in the GitHub repository Asymptote-Labs/agent-beacon (1,834 stars, last pushed today), licensed MIT. It adds 85 tokens to every session and 1,055 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 2026-10-12.
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.