A diagnostic command that checks whether a ThetaCog installation and its coding-agent integrations work on the current computer. It writes a handoff report covering runtimes, add-ons, binaries, demonstrations, the MCP server, and agent skills.

Use it after installation or before handing a setup to someone else; it can also print machine-readable results, check only skills, or fix eligible missing skill files.

It replaces a series of manual setup checks with one recorded result and clearly separates failed checks from checks that could not be measured.

doctor — Skill for Claude Code and Codex by wiber/thetacog-mcp

Install

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.

Any agent

npx skills add wiber/thetacog-mcp --skill doctor

Clone the repo

git clone --depth 1 https://github.com/wiber/thetacog-mcp

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/wiber/thetacog-mcp/doctor/github.svg)](https://agentmods.dev/skills/wiber/thetacog-mcp/doctor)

Your own site

<a href="https://agentmods.dev/skills/wiber/thetacog-mcp/doctor"><img src="https://agentmods.dev/badge/skills/wiber/thetacog-mcp/doctor/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/wiber/thetacog-mcp/doctor"><img src="https://agentmods.dev/badge/skills/wiber/thetacog-mcp/doctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 121 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 701 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00121	$0.00701
Opus 5.5	$0.00048	$0.00280
Sonnet 5.5	$0.00024	$0.00140
Haiku 4.5	$0.00012	$0.00070

Measured yesterday against content hash 40e7b919d67f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

doctor 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.

skills/doctor/SKILL.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/doctor: check this install and write the handoff

One command answers "does everything this install needs actually run here?" — npx thetacog-mcp doctor. Every check is a program with no model in it (THE RECEIPT IS LLM-FREE); a local model, when one answers, adds a labelled note under its own heading and never changes a check result.

Run it

npx thetacog-mcp doctor [--json] [--print] [--no-llm] [--out <file>] [--skills-only] [--fix [--hosts claude-code,cursor,gemini]]

what you want	flag
the full run: runtime, addon, walk binary, demo twice, MCP server, skills	no flags
machine-readable checks	`--json`
the handoff printed to stdout too, not only written	`--print`
skip the local-model note	`--no-llm`
write the handoff somewhere other than `.thetacog/doctor/handoff.md`	`--out <file>`
the fast pass: only whether each agent's skill slot is current	`--skills-only`
write the missing and earlier-ours skill slots (never a foreign file)	`--fix` (narrow with `--hosts`)

Exit 0 when no check FAILED (UNMEASURED is not a failure); exit 1 otherwise.

Read the result

The handoff opens as .thetacog/doctor/handoff.md: every check (PASS, FAIL or UNMEASURED), its detail, and for a FAIL the fix. Read the last line back first — it is the one-line verdict. Paste the whole file into Claude Code, Codex or Grok to wire whatever is left; it names the package map and the exact command each remaining fix needs.

A FAIL on skills:<host> means that agent's .claude/skills (or its adapter's folder) is missing /steer or holds someone else's file at that slot — run npx thetacog-mcp doctor --fix to write the missing and earlier-ours slots. A FAIL never overwrites a foreign SKILL.md; the handoff says whose file is in the way.

What this is sufficient for, and what it is not

It answers whether this install's pieces are present and answer on this host, today. It does not say the work done with them is correct (undecidable, Rice 1953) — only that the runtime, the addon, the walk binary, the demo and the MCP server each ran once and gave the expected shape.

Read the full file on GitHub · 37 lines

Changes

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 · 37 lines · 121 tokens per session scan A 40e7b919d67f

Subscribe to this mod's changes

doctor is a skill published in the GitHub repository wiber/thetacog-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 121 tokens to every session and 701 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.

AI Safety Debugging DevOps and cloud LLM agentic determinism insurance mcp

doctor next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
doctorwiber/thetacog-mcp	Skill	1	yesterday	MIT	A	121	Claude Code, Codex
code-searchagentscope-ai/agentscope-java	Skill	6.3k	today	Apache-2.0	A	38	Claude Code, Codex
reframe-voicesammcj/agentic-coding	Skill	169	3d ago	Apache-2.0	A	49	Claude Code
systematic-debuggingsammcj/agentic-coding	Skill	169	3d ago	Apache-2.0	A	55	Claude Code, Codex
chimera-carry-the-failure-forwardbrcampidelli/chimera-agent	Skill	29	2d ago	Apache-2.0	A	44	Claude Code, Codex
chimera-ground-it-in-the-sourcebrcampidelli/chimera-agent	Skill	29	2d ago	Apache-2.0	A	35	Claude Code, Codex
chimera-when-two-results-contradict-suspect-the-apparatusbrcampidelli/chimera-agent	Skill	29	2d ago	Apache-2.0	A	51	Claude Code, Codex