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 agentmods add skills/onebrain-ai/onebrain/recapnpx skills add onebrain-ai/onebrain --skill recapgit clone --depth 1 https://github.com/onebrain-ai/onebrainWrote 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/onebrain-ai/onebrain/recap)<a href="https://agentmods.dev/skills/onebrain-ai/onebrain/recap"><img src="https://agentmods.dev/badge/skills/onebrain-ai/onebrain/recap.svg" alt="Measured on agentmods" 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 | $0.00086 | $0.02459 |
| Opus 5 | $0.00043 | $0.01229 |
| Sonnet 5 | $0.00017 | $0.00492 |
| Haiku 4.5 | $0.00009 | $0.00246 |
Grade A, and why
recap 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recap
Batch-promotes insights from session logs into memory/ files. Applies frequency filtering to ensure only recurring insights are promoted. Does NOT write to MEMORY.md — Critical Behaviors are promoted exclusively via /learn.
Session Log Discovery
Glob [logs_folder]/session/**/*-session-*.md (post-v2.4.0: session logs live under the dedicated session/ subfolder); filter to files WITHOUT recapped: frontmatter field.
Process only those (faster than scanning all logs).
If no unrecapped logs found → tell user "No unrecapped session logs found." and stop.
Run Threshold
Read recap.min_sessions from onebrain.yml (default: 6 if field absent).
Read recap.min_frequency from onebrain.yml (default: 2 if field absent).
1 unrecapped log: → warn: "Only 1 session log — promotion filter requires at least {min_frequency} sessions." → stop (nothing can pass frequency filter with only 1 log)
2 to (min_sessions - 1) unrecapped logs:
→ warn: "{N}/{min_sessions} sessions — below threshold. Recommended to wait for more sessions. Run recap now?"
→ AskUserQuestion: run-now / wait
→ if wait: stop without processing
≥ min_sessions unrecapped logs: → proceed immediately, no confirmation needed
Promotion Filter (always applied, regardless of log count)
After deciding to proceed, apply frequency filter to all extracted insights:
- Promote only insights whose topic appears in ≥ min_frequency of the session logs being processed
- Single-occurrence insights → skip; insight stays in session log (accessible later via /distill)
Why require recurrence: An insight seen once is an observation. Seen in multiple separate sessions, it becomes evidence of a genuine pattern worth long-term storage. The frequency filter prevents one-off thoughts from cluttering memory/ with noise that quickly becomes stale.
Example (min_frequency=2, 8 logs):
- Topic "recap" → appears in logs 1, 3, 5, 7 → ✅ promote
- Topic "dreaming" → appears in log 2 only → ⏭ skip
- Topic "worktree" → appears in logs 4, 6 → ✅ promote
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 · 219 lines · 86 tokens per session scan A a59ea478854d
recap is a skill published in the GitHub repository onebrain-ai/onebrain (25 stars, last pushed 6d ago), licensed Apache-2.0. It adds 86 tokens to every session and 2,459 once invoked, about $0.0004 per session on Opus 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 2026-08-30.
Other skills, from other repositories
llm-wiki
Build and maintain a persistent, interlinked Obsidian-compatible markdown wiki using Karpathy's LLM Wiki pattern. Extension-backed with auto-generated metadata, guardrails, and 14 custom tools (+3 opt-in agent-trajectory tools).
link-memory
Use after important user-approved decisions, when durable context should be proposed or reviewed, and for explicit Link memory lifecycle work: remember, recall, review, update, archive, restore, forget, or explain local memories through the CLI without requiring MCP.
link-retrieve
Use before answering work that may depend on user memory, project history, source-backed notes, or prior decisions; retrieve compact Link context through the CLI without loading the whole wiki or requiring MCP.
link-ingest
Use when raw files are present, source pages look stale, or a user asks to ingest notes into Link; refresh source-backed wiki pages, propose memories, and validate updates through the CLI without MCP.
lint-brain
Run health checks over the brain vault - find orphan notes, broken wikilinks, missing frontmatter, stale projects, and missing cross-links. Use when asked to "lint the brain", "health check", "vault hygiene", or "/lint-brain".
ingest-article
Ingest an article from a URL or raw text into the brain vault. Extracts key knowledge, determines placement, creates or updates notes, and links to relevant projects. Use when the user shares a URL or text and wants to absorb it into their knowledge base.