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 wiber/thetacog-mcp --skill boardgit clone --depth 1 https://github.com/wiber/thetacog-mcpWrote 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/wiber/thetacog-mcp/board)<a href="https://agentmods.dev/skills/wiber/thetacog-mcp/board"><img src="https://agentmods.dev/badge/skills/wiber/thetacog-mcp/board/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/wiber/thetacog-mcp/board"><img src="https://agentmods.dev/badge/skills/wiber/thetacog-mcp/board.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 | $0.00117 | $0.01959 |
| Opus 5.5 | $0.00047 | $0.00784 |
| Sonnet 5.5 | $0.00023 | $0.00392 |
| Haiku 4.5 | $0.00012 | $0.00196 |
Grade A, and why
Board 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 yesterday.
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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/board — the sheet is the 2-D surface, the record is the source
Operator 2026-10-19, verbatim: "what it is supposed to be is the 2-D surface instead of the 1D chat ... all rooms have the skills to edit these sheets and actually make it a two-way".
The board is a PROJECTION of the repo (spec trees, git, ledgers, the calendar), regenerated, never hand-maintained. Two kinds of cell, never mixed (to1 rule 8): derived cells are ours and are rewritten on every push; (fill) cells are his and are only ever read back.
C1025: /steer reads this board before every cycle. scripts/vna/steer-board-sync.mjs runs the board read, board-answers.mjs route and board-comments.mjs pull before steer.mjs run/until classifies or dispatches a row, so a span or a comment filled here lands on its row first. See .claude/skills/steer/SKILL.md.
The doors (run these; never re-derive them)
| what | command |
|---|---|
| build every tab (xlsx + one CSV per tab) | node scripts/ops/board.mjs --csv out/board/csv (--no-place skips the walk; --sessions <ListAgents.txt> · --calendar <list_events.json>) |
| upload to Drive headless (needs the rclone remote) | node scripts/ops/board.mjs --drive · read back: --pull-drive |
| PULL THE SHEETS (on his ask in chat, and by itself every 5 min): read every changed sheet, land new typed cells, hand each to its room | node scripts/ops/board-watch.mjs (--dry reads only) · the 5-min job: --install / --uninstall (launchd com.thetacog.board-watch, zero tokens unless a sheet changed) · hand-offs: data/vna/board-mailbox.ndjson |
| the one canonical view (Decide · Now · Tasks · Map · Tiles · Questions, named ranges) | node scripts/ops/board-book.mjs (--print [--tab X]) |
| the Now sheet (every terminal: prior · present · future · comment), rewritten on each rest | node scripts/ops/board-now.mjs (--print) |
| rewrite every live sheet IN PLACE (same links), his typed cells carried by id, laid out for a human | node scripts/ops/board-sheets-write.mjs --dry then without --dry (--only <name>) |
| the layout rule (widths, wrap, freeze, tints, machine columns collapsed) | scripts/ops/board-layout.mjs · preview: node scripts/ops/board-sheets-format.mjs --dry |
| append a sheet's filled cells to the record | node scripts/ops/board-answers.mjs pull-csv <export.csv> --tab Questions |
| land each new ANSWER on its spec row, exactly once | node scripts/ops/board-answers.mjs route (--dry first) |
| what is filled but not yet acted on (grades, comments, instructions) | node scripts/ops/board-answers.mjs pending |
| run his comments as /steers in the owning room | node scripts/ops/board-comments.mjs ingest <comments.json> --sheet <name> |
| the pre-decided TOP tab (≤10 decision-ready rows: options, a recommendation, an evidence link) | node scripts/ops/board-top.mjs (send-back bifurcates every row missing a piece to its owning room) |
| the live sheet ids | data/vna/board-drive.json |
| his open decisions (source, hand-maintained) | data/vna/board-decisions.json |
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.
- yesterday First seen · 59 lines · 117 tokens per session scan A 9586d56aff36
Board is a skill published in the GitHub repository wiber/thetacog-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 117 tokens to every session and 1,959 once invoked, about $0.0005 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 2026-11-06.
Board compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Boardwiber/thetacog-mcp | Skill | 1 | yesterday | MIT | A | 117 | Claude Code, Codex |
| xlsxnexus-research-lab/nexus | Skill | 160 | 2d ago | Apache-2.0 | A | 100 | Claude Code |
| Google Workspaceagentic-in/elephant-agent | Skill | 584 | 2mo ago | none | A | 25 | Claude Code, Codex |
| data-analysisbytedance/deer-flow | Skill | 85k | today | MIT | A | 69 | Claude Code, Codex |
| dcf-modelNousResearch/hermes-agent | Skill | 261k | today | MIT | A | 14 | Claude Code, Codex |
| comps-analysisNousResearch/hermes-agent | Skill | 261k | today | MIT | A | 13 | Claude Code, Codex |
| lbo-modelNousResearch/hermes-agent | Skill | 261k | today | MIT | A | 19 | Claude Code, Codex |