Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add atman-33/workhub/plugin install memoryWrote 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/atman-33/workhub/memory-recall)<a href="https://agentmods.dev/skills/atman-33/workhub/memory-recall"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/memory-recall/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/atman-33/workhub/memory-recall"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/memory-recall.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 | $0.00074 | $0.00807 |
| Opus 5.5 | $0.00030 | $0.00323 |
| Sonnet 5.5 | $0.00015 | $0.00161 |
| Haiku 4.5 | $0.00007 | $0.00081 |
Grade A, and why
memory-recall scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 27d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
memory-recall — Search what is remembered
Memory has two stores, and they hold the same history at different stages:
| Store | What is in it | How it is searched |
|---|---|---|
memory/notes/ + memory/episodes/ |
The distilled record: one typed note per decision, lesson or stopped session. In git | cli.mjs notes — type/status filters plus terms |
_ai/state/memory.db |
Every session's verbatim Q&A pairs. This machine only | cli.mjs recall — keyword + vector search |
The distilled record answers first. It is what someone decided was worth keeping, it carries its reasoning, and it is the thing to cite. The verbatim conversation is the raw material behind it: search it when the notes have no answer, or when the exact wording matters.
Steps
-
Parse the arguments: a free-text query and an optional day window.
-
Search the notes.
# terms (all required), in the title or the body node "${CLAUDE_PLUGIN_ROOT}/engine/cli.mjs" notes <terms...> # when the answer has a shape, filter by it node "${CLAUDE_PLUGIN_ROOT}/engine/cli.mjs" notes --type decision --status open node "${CLAUDE_PLUGIN_ROOT}/engine/cli.mjs" notes --type session --status openA superseded decision is left out unless you ask for it (
--status superseded, or--all);--archiveadds archived notes. Matching is literal, so if nothing comes back, try the other word for the same thing before concluding there is no note — "承認" and "確認" do not find each other. -
Search the conversation when the notes did not answer, or to see what was actually said:
# recent timeline (no query) node "${CLAUDE_PLUGIN_ROOT}/engine/cli.mjs" recent --limit 20 # search all time node "${CLAUDE_PLUGIN_ROOT}/engine/cli.mjs" recall "<query>" --limit 5 # search the last N days only node "${CLAUDE_PLUGIN_ROOT}/engine/cli.mjs" recall "<query>" --days 30 --limit 5Add
--fullto print untruncated texts when the clipped output is not enough. With no hits, widen the window stepwise (30 → 90 → 180 days → all time) before concluding the topic was never discussed.
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.
- 27d ago Changed 6374cafacd9f
- 28d ago Changed · +25 lines · +7 tokens per session b74e11a7aa56
- 1mo ago First seen · 46 lines · 67 tokens per session scan A ff4e8f15590a
memory-recall is a skill published in the GitHub repository atman-33/workhub (3 stars, last pushed 2d ago), licensed MIT. It adds 74 tokens to every session and 807 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 2026-09-03.
Other skills, from other repositories
garden-tending
Tend the knowledge garden — diagnose vault health, condense project memos into project.md overviews, create/merge cross-project topics, fix broken links, archive superseded notes, extend trails. Trigger on "tend the garden", "condense", "update project overview", "check vault health", "where are we with X?", "what…
curator-practice
Operating philosophy for autonomous memex curator tending — orientation protocol, signal triage, bounded work units, initiative thresholds, logging conventions. Trigger on cron-launched runs with no user prompt, "use your judgment", "tend without instructions", "do a pass on the vault", "I'll be away — do what needs…
memo-writing
How to write effective session memos — format, frontmatter schema, observation extraction, topic-signal append. Trigger on /memex:save, "save this for later", "remember this", "save what we discussed", "document this session", "create a memo", or when the [memex] activity nudge appears in context. Do NOT trigger for…
recall
Retrieve session memory across 4 modes — TEMPORAL (date browsing), KEYWORD (FTS lookup), DEEP (cross-session synthesis), LOAD (specific file). Trigger on "what did I do yesterday/last week", "why did we...", "remind me...", "find the memo about...", "last time we...", "patterns across projects", "load the X topic". Do…
trellis-update-spec
Captures executable contracts and coding conventions into .trellis/spec/ documents. Use when learning something valuable from debugging, implementing, or discussion that should be preserved for future sessions.
trellis-session-insight
A tool for searching earlier AI conversations through the Trellis memory command-line tool. It retrieves previous discussions, decisions, and solutions related to the current work.