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 standing-answersgit 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/standing-answers)<a href="https://agentmods.dev/skills/wiber/thetacog-mcp/standing-answers"><img src="https://agentmods.dev/badge/skills/wiber/thetacog-mcp/standing-answers/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/standing-answers"><img src="https://agentmods.dev/badge/skills/wiber/thetacog-mcp/standing-answers.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 | $0.00104 | $0.00824 |
| Opus 5.5 | $0.00042 | $0.00330 |
| Sonnet 5.5 | $0.00021 | $0.00165 |
| Haiku 4.5 | $0.00010 | $0.00082 |
Grade A, and why
standing-answers 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 8d 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/standing-answers — draft the ten from the repo, save them where the sidebar reads them
Operator, 2026-10-17, verbatim: "then you can ask claude to refine the answer, think it through (or fill it in with a /skill in claude bsed on the requirements for the repo - then copy the all 10 questions, and currecnt answers..."
1. Read the ten and the current answers
- The questions: the installed extension's own bundled copy, the newest
~/.vscode/extensions/thetadriven.thetacog-mcp-*/out/standing-questions.json(or~/.cursor/...) — never the thetadrivencoach repo'ssrc/lib/backup/standing-answers.mjs, which is not present here. - The current answers: this repo's own
.thetacog/deployer-playbook.jsonif it exists, else draft against an empty playbook (every box blank). Or the operator pastes the "Copy all ten + my answers" block.
2. Draft each answer from the record, never from memory
draft: 'ai'questions (plumber, electrician, demolisher, blast, witness): read the code that runs unattended (its entry point, config, rate limits, the paths it writes) and answer with names a stranger can check: tables, routes, files, commands, numbers. Numbers come from a ledger or config you read, with where you read them.draft: 'you'questions (cause, decides, first hour, wording, level and stop): draft only what the repo shows (who is paged, which actions are held for a person). What only the holder knows (the policy text, the stop date, the price) stays EMPTY so the sidebar badge keeps it open. Never type UNMEASURED into a text box as an answer; an empty box is the honest state.- Read each question's
teachline and stay inside it: the tape measures where the work landed; whether the work was good is undecidable (Rice, 1953). Never promise what the agent will do, never warrant the agent or its outcome.
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.
- 8d ago First seen · 36 lines · 104 tokens per session scan A 212a2bfb816c
standing-answers is a skill published in the GitHub repository wiber/thetacog-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 104 tokens to every session and 824 once invoked, about $0.0004 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 2026-10-30.
standing-answers compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| standing-answerswiber/thetacog-mcp | Skill | 1 | yesterday | MIT | A | 104 | Claude Code, Codex |
| git-checkpointagentscope-ai/agentscope-java | Skill | 6.3k | today | Apache-2.0 | A | 39 | Claude Code, Codex |
| synthesize-reportagentscope-ai/agentscope-java | Skill | 6.3k | today | Apache-2.0 | A | 29 | Claude Code, Codex |
| data-analysisagentscope-ai/agentscope-java | Skill | 6.3k | today | Apache-2.0 | A | 25 | Claude Code, Codex |
| summarizeragentscope-ai/agentscope-java | Skill | 6.3k | today | Apache-2.0 | A | 24 | Claude Code, Codex |
| agent-browserTencent/WeKnora | Skill | 37k | 4d ago | none | A | 83 | Claude Code, Codex |
| skill-creator-primersammcj/agentic-coding | Skill | 169 | 3d ago | Apache-2.0 | A | 74 | Claude Code |