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/countbot-ai/countbot/ima-knowledge-basenpx skills add countbot-ai/CountBot --skill ima-knowledge-basegit clone --depth 1 https://github.com/countbot-ai/CountBotWhat 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 | $0.00067 | $0.00832 |
| Opus 5 | $0.00034 | $0.00416 |
| Sonnet 5 | $0.00013 | $0.00166 |
| Haiku 4.5 | $0.00007 | $0.00083 |
Grade A, and why
ima-knowledge-base 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 2d 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
IMA Knowledge Base
入口:
python skills/ima-knowledge-base/scripts/ima_kb_tool.py <command> ...
执行规则
- 用户说“搜、查、找、看看有没有”时,先
search-kb - 默认直接返回命中片段,不堆字段
search-kb搜的是内容,不是知识库列表- 用户给了
kb-id或kb-name时,加定向参数 - 默认优先
--keyword,只有明确要把多个词合成一次搜索串时才用--query - 宽搜建议加
--show 5 --limit 10;知识库很大再加--search-pages 2或更高
查看单条结果
- 默认先
show-kb-hit - 只有命中像图片、截图、OCR 文档、菜单图,或
show-kb-hit太短时,才用inspect-kb-hit - 一条
--keyword "推荐 菜单 餐厅 美食"会拆成多次搜索,同一标题可能重复出现 - 宽搜后稳定定位优先级:更窄关键词 >
--title>--media-id>--pick
常用命令
python skills/ima-knowledge-base/scripts/ima_kb_tool.py search-kb --keyword "orslow"
python skills/ima-knowledge-base/scripts/ima_kb_tool.py search-kb --keyword "推荐 菜单 餐厅 美食" --show 5 --limit 10
python skills/ima-knowledge-base/scripts/ima_kb_tool.py search-kb --kb-name "个人知识库" --keyword "菜单"
python skills/ima-knowledge-base/scripts/ima_kb_tool.py show-kb-hit --keyword "orslow" --pick 1
python skills/ima-knowledge-base/scripts/ima_kb_tool.py inspect-kb-hit --keyword "orslow" --pick 1
python skills/ima-knowledge-base/scripts/ima_kb_tool.py list-kb
python skills/ima-knowledge-base/scripts/ima_kb_tool.py list-kb-items --kb-name "个人知识库" --limit 20
python skills/ima-knowledge-base/scripts/ima_kb_tool.py upload-file --kb-name "个人知识库" --file "/path/to/report.pdf"
python skills/ima-knowledge-base/scripts/ima_kb_tool.py import-url --kb-name "个人知识库" --url "https://example.com"
推荐类问题
用户问“知识库里有什么推荐”时:
- 先宽搜:
search-kb --keyword "推荐 菜单 餐厅 美食" --show 5 --limit 10 - 命中太杂就补对象词,例如
search-kb --keyword "orslow 推荐" - 锁定单条后先
show-kb-hit - 只有需要 OCR 扩展片段时才
inspect-kb-hit
写入安全
upload-file、import-url会真实写入知识库,执行前先确认目标知识库- 需要配置时查看
scripts/config.json和config.help.md
如何配置
下载最新的IMA客户端(比如Android),登陆后点击 “我” --> Claw配置 --> 复制 client_id和api_key参数,提供给CountBot后会自动调用文件编辑工具修改config.json。
What ships with it
7 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.
- 2d ago First seen · 60 lines · 67 tokens per session scan A c8f30dc2d3a3
ima-knowledge-base is a skill published in the GitHub repository countbot-ai/CountBot (773 stars, last pushed 6d ago), licensed MIT. It adds 67 tokens to every session and 832 once invoked, about $0.0003 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
google-drive-sheets
Find, read, export, edit, and manage the user's Google Drive, Docs, Sheets, and Slides through per-user OAuth.
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
use-shared-credential
When you need to call a service the org has a SHARED credential for (a SERP/search key, a paid-API key, a data-vendor feed, a Git remote) — and the platform has told you that credential is available to this conversation — make the call BY PROXY through the credential broker. You never see the secret; the core stamps…
github-gitlab
Work with GitHub and GitLab repositories through resident gh/glab/git auth on the agent computer.
slack-drafts
Create Slack message drafts in the user's own composer, as the user, through their per-user Slack OAuth. Drafting only — the user reviews and sends from Slack.
deploy-qm
Deploy the QM package from an organization-owned deployment repository to Fly.io or AWS, onboard an administrator, configure connectors, and optionally activate Slack.