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 agentmods add commands/bogzx/seeks/doctorgit clone --depth 1 https://github.com/Bogzx/seeksWrote 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/bogzx/seeks/doctor)<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>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 | $0.00007 | $0.00754 |
| Opus 5 | $0.00003 | $0.00377 |
| Sonnet 5 | $0.00001 | $0.00151 |
| Haiku 4.5 | $0.00001 | $0.00075 |
Grade C, and why
doctor scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Quick fixes: `sudo ln -s "$(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 "${CLAUDE_PLUGIN_ROOT}/bin/seeks.mjs" preflight` (it also flags the common **version-manager-node** trap that `node -v` here would hide), plus `node -v` and `git --version`. If ` What it actually says
Report:
- installed build —
node "${CLAUDE_PLUGIN_ROOT}/bin/seeks.mjs" --version. Quote it in any bug report (/seeks:exportbundles it too);preflightalso returns it asseeks_version.
0b) enforcement is actually running — preflight 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 "${CLAUDE_PLUGIN_ROOT}/bin/seeks.mjs" why <name> --crashes. The hooks are fail-open — a crashed hook allows everything silently — so a non-empty crash list is the single most important thing on this report. Print the errors verbatim and treat it as a bug worth /seeks:export. An empty decision log for a loop that has been running means the hooks never fired at all (check step 1).
-
node+giton PATH — runnode "${CLAUDE_PLUGIN_ROOT}/bin/seeks.mjs" preflight(it also flags the common version-manager-node trap thatnode -vhere would hide), plusnode -vandgit --version. Ifpreflightreturnsok:false(or either is missing), the Stop hook can't run (every stop fails withStop hook error: … node not found) — surface thehintand offer to apply the fix (symlink node onto a system PATH, or add"env":{"PATH":…}to~/.claude/settings.jsonwith consent), then re-runpreflight. Otherwise print this remedy verbatim:- Install Node ≥18 system-wide, not via nvm/fnm/asdf (version managers only put
nodeon interactive shells; hooks run non-interactive). - Quick fixes:
sudo ln -s "$(command -v node)" /usr/local/bin/node; or add"env": { "PATH": "/your/node/bin:/usr/bin:/bin" }to~/.claude/settings.json; or launchclaudefrom a shell wherenode -vworks. - Caveat: this command's shell ≠ the hook's shell, so
nodeshowing up here doesn't prove hooks can see it — if stops still error with "node not found", apply a fix above regardless.
- Install Node ≥18 system-wide, not via nvm/fnm/asdf (version managers only put
-
orphaned worktrees/branches under
.claude/worktrees/vs.seeks/loops/. -
regression probe — for each loop, read
hook-state.jsonstop_fires; if a loop's history shows it repeatedly halting near ~8 fires despite making progress (the signal that the platform's progress-reset broke), advise the user to addCLAUDE_CODE_STOP_HOOK_BLOCK_CAP=0to theirsettings.jsonenv. Note: a plugin cannot self-set this. -
usage tier — print
node "${CLAUDE_PLUGIN_ROOT}/bin/seeks.mjs" tier-get(the active tier + its per-role models and caps, ornoneif unset). Change it withnode … tier-set <light|balanced|all-out>(or edit~/.claude/seeks.json). New loops scaffold from the tier; existing loops keep theirconfig.json.
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.
- 3d ago First seen · 20 lines · 7 tokens per session scan C eb051de38951
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.
Other commands, from other repositories
nio
Nio — scan code, evaluate an action, read the audit report, manage config.
audit
You are in AUDIT MODE. Perform a constitutional compliance scan.
init
You are being initialized as the arifOS Forge Agent on the VPS (srv1325122).
status
Report the current state of the VPS and arifOS project.
forge
You are in FORGE MODE. Execute the following.
_444_ROLLBACK
Command "_444_ROLLBACK" from ariffazil/arifOS, covering scripts → commands consolidation — rollback log, seal: 444rout-ditempa-bukan-diberi-20260523txxxx, status: in progress, pre-consolidation snapshot and migration plan.