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-memory-distillgit 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-memory-distill)<a href="https://agentmods.dev/skills/asymptote-labs/agent-beacon/beacon-memory-distill"><img src="https://agentmods.dev/badge/skills/asymptote-labs/agent-beacon/beacon-memory-distill/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-memory-distill"><img src="https://agentmods.dev/badge/skills/asymptote-labs/agent-beacon/beacon-memory-distill.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 | $0.00109 | $0.03017 |
| Opus 5.5 | $0.00044 | $0.01207 |
| Sonnet 5.5 | $0.00022 | $0.00603 |
| Haiku 4.5 | $0.00011 | $0.00302 |
Grade A, and why
beacon-memory-distill 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 yesterday.
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 — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Beacon memory distill: traces to memory
Beacon captures what agents do in every supported harness. This skill runs the review loop that turns a few of those sessions into approved project memory that any later agent can recall, whichever harness it runs in:
- Pick traces.
- Score them with the evaluator (the one networked step, and only with consent), or, where evaluation is not allowed, skip scoring and read the traces yourself.
- For each candidate, read the source trace and draft the lesson.
- The user confirms, edits, or rejects each draft.
- Approve with the reviewed text.
The evaluator returns probabilities only. It says a trace looks reusable; it does not say what the lesson is. You write the lesson, from the trace, and the user approves it. Never approve a candidate with its placeholder body ("no lesson text was extracted").
Commands that start from a trace (evaluations run, candidates create) file the
memory under the repository the trace recorded, wherever you run them. Run every other
command from inside the repository the memory is for, or pass --project <path>.
Step 1: preflight
beacon version
beacon endpoint traces status --json
- If
beaconis missing, stop and point the user to https://docs.beacon.sh/get-started/overview. Do not install it yourself. - If
statusreports"enabled": false, there is no local history, and only the last day or two of sessions are still in the runtime log. Suggest creating the history, which keeps sessions for 90 days and stays on this machine, and run it only if the user agrees:beacon endpoint traces reindex.
Step 2: pick traces
Use what the user named: a session, a date, a harness, or a topic. Otherwise list recent traces and propose a short set (up to 10) that look like finished work with a correction, a fix, or a non-obvious procedure.
beacon endpoint traces list --json --limit 20
beacon endpoint traces list --json --limit 20 -q "<topic terms>"
beacon endpoint traces search "<error text or file>" --json --limit 10
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday Changed · -1 lines 1563a8ed552d
- 3d ago Changed · +5 lines 5e676d4443f4
- 18d ago Changed · +2 lines 899056356ac7
- 20d ago First seen · 245 lines · 109 tokens per session scan A 4b51f0056afb
beacon-memory-distill is a skill published in the GitHub repository Asymptote-Labs/agent-beacon (1,834 stars, last pushed today), licensed MIT. It adds 109 tokens to every session and 3,017 once invoked, about $0.0004 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 2026-09-26.
Other skills, from other repositories
memory-poisoning-detection
Detect persistent instruction injection or long-term memory poisoning. Focus on writing/retaining hostile instructions for future tasks, not data leakage.
abmind-runtime-operations
Inspect and maintain abmind memory, persona files, sleep, backups, encryption, and runtime health.
abmind_recall_workaround
Fallback when abmind recall / the abmindrecall tool fails — read memories directly from the SQLite DB.
memory-search
Search persistent memory for facts, decisions, and past conversations.
read-messages
Read back raw conversation messages from the abmind messages table (session list + message dump).
topic-save
Save and manage topic-specific knowledge files from conversations.