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 kalinbogatzevski/captain-memo --skill searchgit clone --depth 1 https://github.com/kalinbogatzevski/captain-memoWrote 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/kalinbogatzevski/captain-memo/search)<a href="https://agentmods.dev/skills/kalinbogatzevski/captain-memo/search"><img src="https://agentmods.dev/badge/skills/kalinbogatzevski/captain-memo/search/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/kalinbogatzevski/captain-memo/search"><img src="https://agentmods.dev/badge/skills/kalinbogatzevski/captain-memo/search.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 | $0.00049 | $0.00503 |
| Opus 5.5 | $0.00020 | $0.00201 |
| Sonnet 5.5 | $0.00010 | $0.00101 |
| Haiku 4.5 | $0.00005 | $0.00050 |
Grade A, and why
search 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 21d 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
Captain Memo — direct search
When the user invokes this skill, they want a direct hybrid search against Captain Memo's local index. Don't reason about it — just run it.
What to do
- Take the user's argument as the query string (everything after
/captain-memo:search). - Call the captain-memo MCP tool
search_allwithqueryset to that string andtop_kset to5. Show the user the formatted result.
The MCP server talks to the worker and sends the worker's secret for you: there is nothing to quote and no token to handle.
The result is { results: [{ score, channel, title, doc_id, snippet, ... }] }. Show score to two decimals and cut each snippet to about 200 characters.
Format the output as
3 hits for "the user's query":
[0.94] memory · feedback_no_mocked_db
doc_id: memory:feedback_no_mocked_db:abc1234
In this project, do NOT mock the database in integration tests…
[0.87] memory · feedback_use_real_fixtures
doc_id: memory:feedback_use_real_fixtures:def5678
…
[0.82] observation · 2026-04-30 · "Fix off-by-one in pagination loop"
doc_id: observation:1700000000:ghi9012
…
Tip the user: they can run /captain-memo:recall <doc_id> to fetch the full content of any hit.
On error
- The tool errors with 503 or the worker is not reachable: tell the user to run
captain-memo doctorto diagnose - The tool errors with 401: the call carried no valid worker secret (a session started before 0.52.0 sends none). Tell the user to restart the AI session;
captain-memo doctorlists the routes still called without one - Empty results: say "no hits — try a more specific query, or check
captain-memo statsto confirm the corpus is indexed"
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.
- 21d ago Changed · -4 lines 0146bfb0f574
- 1mo ago First seen · 48 lines · 49 tokens per session scan A 43f15f31b1f4
search is a skill published in the GitHub repository kalinbogatzevski/captain-memo (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 49 tokens to every session and 503 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 2026-08-31.
Other skills, from other repositories
memem-mine
Opt in to memem's event-triggered mining. New sessions are mined automatically via the Stop hook.
wenlan-handoff
End a work session. Stores durable captures, writes a narrative session log, and automatically applies typed item-level deltas to the current Space Brief. Invoked as /wenlan-handoff.
curate
Power-user audit of Wenlan's pending surfaces: accept or dismiss pending revisions (conflicts/merges), or audit pending captures (not yet confirmed). Most users want /brief for revisions; that handles the daily flow. Use /wenlan curate only for explicit deep-walk audits after bulk imports, or to walk the full queue…
wenlan-capture
Save a memory to Wenlan in flow, or save something from this conversation as one note when the user asks for a note. Use proactively when the user states a preference, makes a decision, corrects you, or shares a durable fact. Invoked as /wenlan-capture .
wenlan
A single command entry point for Wenlan, a tool that checks its setup and connection and turns stored memories into notes. It can also open or list notes and report its current status.
wenlan-recall
Search Wenlan's local memory by query. Targeted lookup, not orientation. Invoked as /wenlan-recall . Use when the user asks "do you remember", "what do you know about", "look up".