Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/wiber/thetacog-mcpnpx agentmods add skills/wiber/thetacog-mcp/sheetWrote 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/sheet)<a href="https://agentmods.dev/skills/wiber/thetacog-mcp/sheet"><img src="https://agentmods.dev/badge/skills/wiber/thetacog-mcp/sheet/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/sheet"><img src="https://agentmods.dev/badge/skills/wiber/thetacog-mcp/sheet.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 | $0.00127 | $0.01402 |
| Opus 5.5 | $0.00051 | $0.00561 |
| Sonnet 5.5 | $0.00025 | $0.00280 |
| Haiku 4.5 | $0.00013 | $0.00140 |
Grade A, and why
Sheet 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sheet — the Google Sheets door a stranger can run themselves
(chair decomposition 2026-11-05 of the operator's words "/steer infer all the features we need to bundle here. So what do we really need to ship with this for the /dir command to be as compelling as possible? We alrea", not on the tape: "Spec adherence ships inside the npm package, and the sheets are how a stranger sees it. — Bundle the Google Sheets integration as skills in the package: /board, /tend and /project, plus a new /sheet skill that, after the person signs into Google once, creates a sheet for a steer run that itemises every ask of that run and of the extension in general, one row per ask with its plain head, verbatim span, guard, state, commit and Merkle leaf, at maximum density so the eye reads it at once, and an option to write the spec Merkle tree as a sheet.")
The sheets are how a stranger sees it. /board, /tend and /project are built for an operator who already holds a Drive folder. /sheet is the narrower door: the one Google sign-in, then one sheet.
The one sign-in
Every sheet door in this package reads the same token: an rclone remote named thetacog-gdrive with scope=drive. Sign in once:
rclone config create thetacog-gdrive drive scope=drive
node scripts/ops/board-asks.mjs checks this before any write and prints UNMEASURED — <why> — sign in to Google once, then re-run and stops cleanly when it is missing — it never guesses a folder or creates one without the sign-in.
The ask sheet
node scripts/ops/board-asks.mjs --print [--rows C1,C2] [--date YYYY-MM-DD]
node scripts/ops/board-asks.mjs [--rows C1,C2] [--date YYYY-MM-DD]
Writes the sheet Asks (created on the first run, in the Drive folder named in data/vna/board-drive.json; rewritten cell by cell after that). One tab, one header, the same layout the operator reads on Steer · Compiled: both are composed by one function, composeAsksTab() in scripts/ops/board-steer.mjs, so what this package writes is what he sees.
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 · 65 lines · 127 tokens per session scan A 38f62b2d7626
Sheet is a skill published in the GitHub repository wiber/thetacog-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 127 tokens to every session and 1,402 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.
Sheet compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Sheetwiber/thetacog-mcp | Skill | 1 | yesterday | MIT | A | 127 | 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 |