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 licencegit 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/licence)<a href="https://agentmods.dev/skills/wiber/thetacog-mcp/licence"><img src="https://agentmods.dev/badge/skills/wiber/thetacog-mcp/licence/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/licence"><img src="https://agentmods.dev/badge/skills/wiber/thetacog-mcp/licence.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 | $0.00153 | $0.01485 |
| Opus 5.5 | $0.00061 | $0.00594 |
| Sonnet 5.5 | $0.00031 | $0.00297 |
| Haiku 4.5 | $0.00015 | $0.00148 |
Grade A, and why
licence 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/licence — your licence, from the CLI
The install and the measurement are free and open-source (MIT); only the financialization/attestation layer is licensed. This skill runs that licensed layer from a terminal, with the same doors the ThetaCog extension's 🔑 pills open. Every command is a door of the published package, npx thetacog-mcp <door>, so it works in any folder. If a door below fails with "unknown command", the installed package is older than this skill: run npx -y thetacog-mcp@latest skills and try again.
Login, payment and the licence itself happen on thetadriven.com, never in this terminal. This skill opens the page, waits for the site, and checks what comes back. auth-flow connect and auth-flow notarise contact thetadriven.com and wait up to 10 minutes for the site to answer; every other door here runs on this machine alone. It never asks for a card, a password or a key in chat.
The device key is this machine's own signing key, kept in the keychain; it is the key a licence is bound to. whoami below only reads it — it never creates one, so asking for your identity never touches the keychain. Only a door that connects, buys, pastes a key or signs something mints a device key if this machine does not already hold one.
The doors
| what you want | door |
|---|---|
| which licence this machine holds (credits, account, expiry) | npx thetacog-mcp auth-flow entitlement |
| this machine's identity (the key the licence binds to) | npx thetacog-mcp auth-flow whoami |
| connect this machine / buy credits (opens the site, then waits) | npx thetacog-mcp auth-flow connect |
| fund a notarisation of the tape (the 💳) | npx thetacog-mcp auth-flow notarise |
| paste a licence key by hand (the key rides stdin, never argv) | pbpaste | npx thetacog-mcp auth-flow verify --jwt - |
| sign a commit under the licence | npx thetacog-mcp auth-flow sign --sha HEAD |
| check a signed row's licence stamp | npx thetacog-mcp auth-flow verify-licence --row - < row.json |
| back up the tape for countersigning (bundle, then the /backup URL) | npx thetacog-mcp backup |
| check a licence tape offline (signatures, hash chain, one signer; refuses a revoked licence) | npx thetacog-mcp verify-license --tape tape.json [--license lic_<id>] |
| countersign a receipt as deployer or insurer, then check the circle | npx thetacog-mcp attest-countersign sign --receipt r.json --role deployer --as "<name>" · npx thetacog-mcp attest-countersign circle --receipt r.json |
| disconnect this machine | npx thetacog-mcp auth-flow entitlement --clear |
| are the skills installed, which versions (the debug page) | npx thetacog-mcp skills --debug |
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 · 44 lines · 153 tokens per session scan A a166110e5d97
licence is a skill published in the GitHub repository wiber/thetacog-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 153 tokens to every session and 1,485 once invoked, about $0.0006 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.
licence compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| licencewiber/thetacog-mcp | Skill | 1 | yesterday | MIT | A | 153 | Claude Code, Codex |
| ap-models-authagentproto/ts | Skill | 9 | today | Apache-2.0 | A | 69 | Claude Code, Codex |
| billingfootprintjs/agentfootprint | Skill | 21 | yesterday | MIT | A | 15 | Claude Code, Codex |
| finanz-versicherungellmos-ai/skills | Skill | 9 | today | MIT | A | 27 | Claude Code, Codex |
| ai-unit-economicsVandanaAjayDubey111/great-pm | Skill | 3 | 1mo ago | MIT | A | 94 | Claude Code |
| cost-modelVandanaAjayDubey111/great-pm | Skill | 3 | 1mo ago | MIT | A | 65 | Claude Code |
| pm-costVandanaAjayDubey111/great-pm | Skill | 3 | 1mo ago | MIT | A | 46 | Claude Code, Codex |