doctor

doctor is a command for coding agents from Bogzx/seeks. It costs 7 tokens per session (754 once invoked), scanned C, original, MIT.

A health-check command for seeks, a system that runs coding work in tracked loops. It checks the installation, required tools, safety hooks, and recent hook crashes.

In plain words
What is it for?
Use it to diagnose Node.js and Git setup, check enforcement settings, inspect crash records, and gather bug-report details.
Why use it?
It helps explain why loop controls may not be working, especially when a crashed safety hook silently allows an action.

Command

Part of the seeks plugin — 1 skill, 10 commands, 3 hooks shipped together

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.

agentmods
npx agentmods add commands/bogzx/seeks/doctor
Clone the repo
git clone --depth 1 https://github.com/Bogzx/seeks

Or install seeks, the plugin that ships this one along with the rest of its 1 skill, 10 commands, 3 hooks.

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.

agentmods badge for doctor

README.md
[![agentmods](https://agentmods.dev/badge/commands/bogzx/seeks/doctor.svg)](https://agentmods.dev/commands/bogzx/seeks/doctor)
Your own site
<a href="https://agentmods.dev/commands/bogzx/seeks/doctor"><img src="https://agentmods.dev/badge/commands/bogzx/seeks/doctor.svg" alt="Measured on agentmods" height="20"></a>
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 754 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00007 $0.00754
Opus 5 $0.00003 $0.00377
Sonnet 5 $0.00001 $0.00151
Haiku 4.5 $0.00001 $0.00075

Measured 3d ago against content hash eb051de38951, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

doctor scanned grade C with 2 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 3d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- Quick fixes: `sudo ln -s "$(command -v node)" /usr/local/bin/node`; **or** add `"env": { "PATH": "/your/node/bin:/usr/bin:/bin" }` to `~/.claude/settings.json`; **or** launch `claude` from a shell where `node -v` works

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

1) **`node` + `git` on PATH** — run `node "${CLAUDE_PLUGIN_ROOT}/bin/seeks.mjs" preflight` (it also flags the common **version-manager-node** trap that `node -v` here would hide), plus `node -v` and `git --version`. If `
commands/doctor.md · 20 lines

What it actually says

Report:

  1. installed buildnode "${CLAUDE_PLUGIN_ROOT}/bin/seeks.mjs" --version. Quote it in any bug report (/seeks:export bundles it too); preflight also returns it as seeks_version.

0b) enforcement is actually runningpreflight returns strict_bash (is SEEKS_STRICT_BASH on for this session?) and strict_bash_allow (the active Bash allowlist); report both. Then, for the most recent loop, run node "${CLAUDE_PLUGIN_ROOT}/bin/seeks.mjs" why <name> --crashes. The hooks are fail-open — a crashed hook allows everything silently — so a non-empty crash list is the single most important thing on this report. Print the errors verbatim and treat it as a bug worth /seeks:export. An empty decision log for a loop that has been running means the hooks never fired at all (check step 1).

  1. node + git on PATH — run node "${CLAUDE_PLUGIN_ROOT}/bin/seeks.mjs" preflight (it also flags the common version-manager-node trap that node -v here would hide), plus node -v and git --version. If preflight returns ok:false (or either is missing), the Stop hook can't run (every stop fails with Stop hook error: … node not found) — surface the hint and offer to apply the fix (symlink node onto a system PATH, or add "env":{"PATH":…} to ~/.claude/settings.json with consent), then re-run preflight. Otherwise print this remedy verbatim:

    • Install Node ≥18 system-wide, not via nvm/fnm/asdf (version managers only put node on interactive shells; hooks run non-interactive).
    • Quick fixes: sudo ln -s "$(command -v node)" /usr/local/bin/node; or add "env": { "PATH": "/your/node/bin:/usr/bin:/bin" } to ~/.claude/settings.json; or launch claude from a shell where node -v works.
    • Caveat: this command's shell ≠ the hook's shell, so node showing up here doesn't prove hooks can see it — if stops still error with "node not found", apply a fix above regardless.
  2. orphaned worktrees/branches under .claude/worktrees/ vs .seeks/loops/.

  3. regression probe — for each loop, read hook-state.json stop_fires; if a loop's history shows it repeatedly halting near ~8 fires despite making progress (the signal that the platform's progress-reset broke), advise the user to add CLAUDE_CODE_STOP_HOOK_BLOCK_CAP=0 to their settings.json env. Note: a plugin cannot self-set this.

  4. usage tier — print node "${CLAUDE_PLUGIN_ROOT}/bin/seeks.mjs" tier-get (the active tier + its per-role models and caps, or none if unset). Change it with node … tier-set <light|balanced|all-out> (or edit ~/.claude/seeks.json). New loops scaffold from the tier; existing loops keep their config.json.

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.

  1. 3d ago First seen · 20 lines · 7 tokens per session scan C eb051de38951

Subscribe to this mod's changes

doctor is a command published in the GitHub repository Bogzx/seeks (4 stars, last pushed 16d ago), licensed MIT. It adds 7 tokens to every session and 754 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it C with 2 findings (asks for root, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.