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/heptameta/heptabase-cli-skills/heptabase-clinpx skills add heptameta/heptabase-cli-skills --skill heptabase-cligit clone --depth 1 https://github.com/heptameta/heptabase-cli-skillsWrote 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/heptameta/heptabase-cli-skills/heptabase-cli)<a href="https://agentmods.dev/skills/heptameta/heptabase-cli-skills/heptabase-cli"><img src="https://agentmods.dev/badge/skills/heptameta/heptabase-cli-skills/heptabase-cli.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 5.1 | $0.00107 | $0.02751 |
| Opus 5 | $0.00053 | $0.01375 |
| Sonnet 5 | $0.00021 | $0.00550 |
| Haiku 4.5 | $0.00011 | $0.00275 |
Grade A, and why
heptabase-cli 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 6d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prerequisites
- CLI installed from the desktop app. The command is
heptabaseon macOS/Linux; Windows installsheptabase.cmdfor cmd/PowerShell and aheptabaseshim for POSIX shells. - Check version compatibility before use with
heptabase --version. If the installed CLI version is outside this skill's compatibility range (0.6.x), you MUST stop and ask the user to update either the Heptabase desktop app or this skill package before continuing.
Command discovery
Run heptabase help to see all available top-level commands. This is always up to date. Each command supports --help for detailed usage:
heptabase help
heptabase note --help
heptabase note create --help
Common recipes
Use these as quick recipes for frequent requests. For less common flags or if a command fails, run heptabase help or <command> --help to discover the correct syntax.
- Recent cards:
heptabase card list --sort createdTime --direction descending --limit 20 - Today's journal:
heptabase journal read $(date +%Y-%m-%d) - Search cards by keyword:
heptabase card list -q "<keyword>" --limit 20 - Create a note from markdown:
heptabase note create --content "# Title\n\nBody"(marks Created by AI by default; add--no-created-by-aifor human-owned content). - Create today's journal from markdown:
heptabase journal create --content "Body"(marks Created by AI by default; add--no-created-by-aifor human-owned content). - Append markdown to a note:
heptabase note append <cardId> --content "More content". - Edit note content with JSON save: first read
references/card-content-schema.md, then useheptabase note read <cardId>, modify the returned ProseMirror JSON, and save withheptabase note save <cardId> --content-md5 <contentMd5> --content-file <path>. - Work with properties: use
heptabase tag cards <tagId> --include-propertiesto list tagged cards with values, orheptabase card properties <cardIdOrDate>to inspect one card. Before writing, readreferences/property-values.md, inspect definitions withheptabase tag properties <tagId>, then useheptabase card set-property <cardIdOrDate> --property-id <propertyId> --value "Published"for strings/options or--json-value ...for typed JSON values. - Read parsed PDF content: first read
references/pdf-reading.md, then useheptabase pdf metadata <pdfCardId>to discovertotalPages, and read a page range withheptabase pdf read <pdfCardId> --start-page N --end-page N. - Read transcript content: first read
references/transcript-reading.md, then useheptabase audio metadata <audioCardId>orheptabase video metadata <videoCardId>to discovertranscriptStatusanddurationSeconds, and read overlapping transcript entries in a time range withheptabase audio read <audioCardId> --start-seconds 0 --end-seconds 300orheptabase video read <videoCardId> --start-seconds 0 --end-seconds 300. - Read an attached file: first read
references/file-reading.md. If needed, find its ID withheptabase file list --card-id <cardId>, then runmktemp -dandheptabase file export <fileId> --output-dir <scratchDir>. Read the returnedpathwith your native file-reading tool. - Inspect a whiteboard:
heptabase whiteboard read <whiteboardId> --mode structure, thenheptabase whiteboard read-layout <whiteboardId>. - Read chat messages: Copy a chat ID from
whiteboard readoutput, then useheptabase object read chat <chatId> --offset <n> --limit <n>to paginate non-removed messages with their displayed author, timestamp, quoted content, and message content. For a whiteboard chat-messages element, useheptabase object read chatMessagesElement <elementId> --offset <n> --limit <n>. - Check or view whiteboard layout: run
heptabase whiteboard lint <whiteboardId>. For visual review, first readreferences/whiteboard.md, then useheptabase whiteboard screenshot <whiteboardId> --output <existingDirectory>/whiteboard.pngand inspect the returned local path. - Change whiteboard layout or a mind map: first read
references/whiteboard.md; for mind maps, also readreferences/mind-maps.md. Commands with nested or batch input use--input <path|->and canonical JSON.
What ships with it
9 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.
- references/card-content-schema.md 17 KB
- references/codex-sandbox.md 790 B
- references/created-by-ai.md 1.5 KB
- references/file-reading.md 3.0 KB
- references/mind-maps.md 7.3 KB
- references/pdf-reading.md 1.2 KB
- references/property-values.md 4.2 KB
- references/transcript-reading.md 1.6 KB
- references/whiteboard.md 11 KB
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.
- 6d ago First seen · 122 lines · 107 tokens per session scan A c80f352e80fc
heptabase-cli is a skill published in the GitHub repository heptameta/heptabase-cli-skills (149 stars, last pushed 9d ago), licensed MIT. It adds 107 tokens to every session and 2,751 once invoked, about $0.0005 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.