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/craftos-dev/craftbot/feishu-memory-recallnpx skills add CraftOS-dev/CraftBot --skill feishu-memory-recallgit clone --depth 1 https://github.com/CraftOS-dev/CraftBotWrote 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/craftos-dev/craftbot/feishu-memory-recall)<a href="https://agentmods.dev/skills/craftos-dev/craftbot/feishu-memory-recall"><img src="https://agentmods.dev/badge/skills/craftos-dev/craftbot/feishu-memory-recall.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 | $0.00022 | $0.00583 |
| Opus 5 | $0.00011 | $0.00292 |
| Sonnet 5 | $0.00004 | $0.00117 |
| Haiku 4.5 | $0.00002 | $0.00058 |
Grade A, and why
feishu-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 5d 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
Feishu Memory Recall
Cross-group awareness for OpenClaw. Search messages, generate digests, and share events across all Feishu groups and DMs.
Commands
| Command | Description |
|---|---|
recall --user <id> [--hours 24] |
Find messages from a user across all groups |
search --keyword <text> [--hours 24] |
Search messages by keyword across all groups |
digest [--hours 6] |
Activity summary of all tracked groups |
log-event -s <source> -e <text> |
Write event to RECENT_EVENTS.md + daily log |
sync-groups |
Auto-discover groups from gateway sessions |
add-group -i <id> -n <name> |
Manually track a group |
list-groups |
Show tracked groups |
Usage
# Search for "GIF error" across all groups
node skills/feishu-memory-recall/index.js search -k "GIF" --hours 12
# What happened in all groups in the last 6 hours?
node skills/feishu-memory-recall/index.js digest --hours 6
# Log a cross-session event
node skills/feishu-memory-recall/index.js log-event -s "dev-group" -e "Fixed GIF crash in gateway"
# Auto-discover all Feishu groups from gateway sessions
node skills/feishu-memory-recall/index.js sync-groups
# Find what a specific user said recently
node skills/feishu-memory-recall/index.js recall -u ou_cdc63fe05e88c580aedead04d851fc04 --hours 48
How It Works
- sync-groups: Reads
~/.openclaw/agents/main/sessions/sessions.jsonto auto-discover all Feishu groups the agent is connected to. - search/recall/digest: Calls Feishu API to fetch messages from tracked groups, filters by keyword/user/time.
- log-event: Appends to both
RECENT_EVENTS.md(rolling 24h cross-session feed) andmemory/YYYY-MM-DD.md(permanent daily log).
Configuration
Requires Feishu credentials in .env:
FEISHU_APP_ID=cli_xxxxx
FEISHU_APP_SECRET=xxxxx
Group list is stored in memory/active_groups.json and can be auto-populated via sync-groups.
What ships with it
5 files 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.
- 5d ago First seen · 58 lines · 22 tokens per session scan A ce8128fee1d7
feishu-memory-recall is a skill published in the GitHub repository CraftOS-dev/CraftBot (376 stars, last pushed 2d ago), licensed MIT. It adds 22 tokens to every session and 583 once invoked, about $0.0001 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
feishu-memory-recall
Cross-group memory, search, and event sharing for OpenClaw Feishu agents.
feishu-memory-recall
Cross-group memory, search, and event sharing for OpenClaw Feishu agents.
metabot
Unified MetaBot CLI for personal Memory, Skill Hub, durable Agent Bus messaging, agent registry, Agent Teams, T5T, scheduling, and bridge runtime operations.
memory
Unified read-side memory operations including knowledge graph search, session context loading, decision timeline viewing, and Mermaid graph visualization. Subcommands: search, load, history, viz, status. Complements /ork:remember (write-side). Use when searching past decisions, loading context, or visualizing the…
frontmcp-extensibility
Use when extending FrontMCP beyond the core SDK by integrating external npm packages, libraries, or third-party services into providers and tools. Covers VectoriaDB for in-memory semantic and vector search (ML-based embeddings or TF-IDF keyword engines, with persistence) and the tamper-evident, hash-chained skill…
forgetful-recall
Recall past knowledge before working — prior decisions, solved problems, preferences, project history. Use at the start of any task, when the user references earlier work, when re-entering a project after time away, or before proposing an approach that may already have history. Covers query shaping, scoping…