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.
git clone --depth 1 https://github.com/entropyeq/karpathy-plusWrote 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/commands/entropyeq/karpathy-plus/wiki-doctor)<a href="https://agentmods.dev/commands/entropyeq/karpathy-plus/wiki-doctor"><img src="https://agentmods.dev/badge/commands/entropyeq/karpathy-plus/wiki-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.
<a href="https://agentmods.dev/commands/entropyeq/karpathy-plus/wiki-doctor"><img src="https://agentmods.dev/badge/commands/entropyeq/karpathy-plus/wiki-doctor.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 | $0.00015 | $0.00226 |
| Opus 5 | $0.00008 | $0.00113 |
| Sonnet 5 | $0.00003 | $0.00045 |
| Haiku 4.5 | $0.00002 | $0.00023 |
Grade A, and why
wiki-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 10d 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.
What it actually says
Run the doctor script and interpret its results:
bash ~/.claude/hooks/wiki-doctor.sh
It checks the whole install chain mechanically: wiki path resolves, INDEX.md exists, both hooks are present and wired in valid settings.json, the session-end hook is actually configured (not placeholders), the SessionStart injection really produces the index, and the wiki is a git repo with a remote and a .gitignore.
Then:
- Report the output to the user, PASS lines compressed to one summary line, each WARN/FAIL quoted with its fix hint.
- For each FAIL, offer to apply the fix now (they map to SETUP.md steps 2-4). Fix only with the user's go-ahead, one at a time, re-running the doctor after each to confirm.
- If everything passes and the user was debugging a retrieval problem ("Claude doesn't know X"), the install chain is not the culprit: check instead whether the fact is actually on a wiki page that INDEX.md links.
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.
- 10d ago First seen · 18 lines · 15 tokens per session scan A ca886d3310d4
wiki-doctor is a command published in the GitHub repository entropyeq/karpathy-plus (5 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 226 once invoked, about $0.0001 per session on Opus 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 2026-08-31.
Other commands, from other repositories
unbloat
Remove dead code, duplicate files, and unused dependencies with user approval at each step. Backs up before deleting.
fix-issue
Fixes GitHub issues using parallel analysis agents for root cause investigation, code exploration, and regression detection. Reads issue context from gh CLI, searches codebase and memory for related patterns, generates a fix with tests, and links the resolution back to the issue via PR. Includes prevention analysis to…
payload-revert
Stage reverts for high-confidence payload candidates identified by payload-analysis.
bug-fix
Streamlines bug fixing by creating a GitHub issue first, then a feature branch for implementing and thoroughly testing the solution before merging.
CLAUDE
When debugging TUI commands like wt switch (interactive picker), use the tmux-cli skill (preferred) or MCP's node-terminal tools to test interactively.
fix-issue
Analyze and fix the GitHub issue: $ARGUMENTS.