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 Jarroslav/agentic-os --skill agentic-doctorgit clone --depth 1 https://github.com/Jarroslav/agentic-osWrote 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/jarroslav/agentic-os/agentic-doctor)<a href="https://agentmods.dev/skills/jarroslav/agentic-os/agentic-doctor"><img src="https://agentmods.dev/badge/skills/jarroslav/agentic-os/agentic-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/jarroslav/agentic-os/agentic-doctor"><img src="https://agentmods.dev/badge/skills/jarroslav/agentic-os/agentic-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 | $0.00184 | $0.06107 |
| Opus 5 | $0.00092 | $0.03053 |
| Sonnet 5 | $0.00037 | $0.01221 |
| Haiku 4.5 | $0.00018 | $0.00611 |
Grade C, and why
agentic-doctor scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
WORK="$(mktemp -d)"; trap 'rm -rf "$WORK"' EXIT How it starts
The opening of the file, as written. The whole thing — 447 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agentic-doctor — install verifier
Read-only except for two things: .agentic/agentic-os/doctor.json (the
verdict) and the temporary probe contract Check 3 creates and deletes. You
never fix anything — you diagnose, report, and write the verdict. TARGET =
the current repo root (git rev-parse --show-toplevel).
Resolve the canonical agent, skill and state directories from
journal.adoption rather than assuming .agentic/ — an adopted fleet keeps its
own layout. Files recorded as origin: "adopted-existing" belong to the user:
a missing one is a warning, and hash drift is information, not a fault. Finding
contracts in both .agents/agents/ and .agentic/agents/ is a failure —
that is the competing-fleet state the installer refuses to create, so seeing it
here means something else made it.
On Codex, additionally verify that agentic-os, agentic-sdlc and the required
superpowers version are enabled; that plugin hooks are enabled; that journaled
Codex TOML agents parse and point at canonical contracts; that journaled rules
exist; and that hook commands resolve from git rev-parse --show-toplevel.
Never read authentication values — their presence is checkable without their
contents.
Precondition: TARGET/.agentic/agentic-os/install.json exists (the install
journal written by /agentic-init). Missing ⇒ report "not installed — run
/agentic-init" and write a failed doctor.json with only that finding.
Collect results into checks (each check: passed bool + detail), plus
failures (flat list of failed-check messages) and pending_restart (plugin
names). Run every check even after failures — the report must be complete.
Check 1 — File manifest vs journal
For every entry in journal.files:
- File missing ⇒ fail (
manifest), unlessowner: "user"with a skip origin (a skipped collision journals the pre-existing file — its absence is still worth a warning, not a failure). - Current sha256 (
shasum -a 256) differs from journaled ⇒ not a failure: report asmodified(expected forowner: "user"; forowner: "managed"it means local edits an upgrade will prompt about; forowner: "generated"it means the contract drifted from its audited state — cross-check Check 7).
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 447 lines · 0 tokens per session scan C dcf9719001da
agentic-doctor is a skill published in the GitHub repository Jarroslav/agentic-os (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 184 tokens to every session and 6,107 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.