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 Tenon-Net/TenonAdmin --skill doctorgit clone --depth 1 https://github.com/Tenon-Net/TenonAdminWrote 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/tenon-net/tenonadmin/doctor)<a href="https://agentmods.dev/skills/tenon-net/tenonadmin/doctor"><img src="https://agentmods.dev/badge/skills/tenon-net/tenonadmin/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/skills/tenon-net/tenonadmin/doctor"><img src="https://agentmods.dev/badge/skills/tenon-net/tenonadmin/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 | $0.00023 | $0.00549 |
| Opus 5.5 | $0.00009 | $0.00220 |
| Sonnet 5.5 | $0.00005 | $0.00110 |
| Haiku 4.5 | $0.00002 | $0.00055 |
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 today.
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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OMX Doctor
Repository-wide authority, state, and cancellation rules live in AGENTS.md. Diagnose exact paths and ownership before changing installation state.
Diagnose
Run the smallest command that covers the reported failure:
omx doctor
omx doctor --verbose
omx doctor --team
omx doctor --dry-run --force
For a local source checkout, build first and invoke node dist/cli/omx.js doctor. Record the command, exit status, exact failing paths, detected versions, and relevant output. With --team, retain any resume_blocker, slow_shutdown, delayed_status_lag, stale_leader, or orphan_tmux_session evidence.
Inspect only the surfaces implicated by that evidence:
- active package/plugin version and duplicate cache entries;
- hook references in
config.tomlor legacysettings.json, plus the referenced hook files; - the applicable global and repository
AGENTS.mdfiles and their managed markers; - discovered skill roots and duplicate skill names;
- legacy OMX-owned
agents/orcommands/artifacts; - Team state only when Team diagnostics were requested.
.agents/skills and ~/.agents/skills are supported Codex skill locations, not legacy content by definition. .codex/skills may also contain installed or repository-local skills. Report a conflict only when concrete duplicate names or stale OMX-owned artifacts affect discovery.
Repair
Apply already-authorized, reversible repairs to the exact confirmed target, then rerun the failing diagnostic. Prefer the installer or CLI's targeted repair command, an in-place managed-block update, or moving one confirmed legacy artifact to a named backup.
Before deleting, replacing, or overwriting data, identify the exact path, prove it is OMX-owned, preserve unrelated content, and obtain confirmation when that destructive action is not already authorized. Never remove an entire skill, agent, command, hook, cache, or configuration tree because one entry is stale.
For a missing or outdated AGENTS.md, compare the installed release template with the applicable file and update only the authorized target while preserving repository and user customizations. Treat remote documentation as reference material, not as content to overwrite a global instruction file wholesale.
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.
- today First seen · 45 lines · 23 tokens per session scan A 170ccb1056cd
doctor is a skill published in the GitHub repository Tenon-Net/TenonAdmin (41 stars, last pushed 14d ago), licensed Apache-2.0. It adds 23 tokens to every session and 549 once invoked, about $0.0001 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 2026-11-07.
doctor compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| doctorTenon-Net/TenonAdmin | Skill | 41 | 14d ago | Apache-2.0 | A | 23 | Codex |
| analyzer-developmentFritzAndFriends/BlazorWebFormsComponents | Skill | 455 | 4mo ago | MIT | A | 84 | Claude Code, Codex |
| dotnet-reversezhaoxuya520/reverse-skill | Skill | 44k | 1mo ago | MIT | A | 144 | Claude Code |
| check-bin-obj-clashdotnet/skills | Skill | 5.8k | yesterday | MIT | A | 160 | Claude Code |
| winforms-expertdotnet/skills | Skill | 5.8k | yesterday | MIT | A | 137 | Claude Code |
| build-perf-diagnosticsdotnet/skills | Skill | 5.8k | yesterday | MIT | A | 133 | Claude Code |
| dump-collectdotnet/skills | Skill | 5.8k | yesterday | MIT | A | 96 | Claude Code |