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 jstoup111/ai-conductor --skill daemon-triagegit clone --depth 1 https://github.com/jstoup111/ai-conductorWrote 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/jstoup111/ai-conductor/daemon-triage)<a href="https://agentmods.dev/skills/jstoup111/ai-conductor/daemon-triage"><img src="https://agentmods.dev/badge/skills/jstoup111/ai-conductor/daemon-triage/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/jstoup111/ai-conductor/daemon-triage"><img src="https://agentmods.dev/badge/skills/jstoup111/ai-conductor/daemon-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 304 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 29 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00069 | $0.03801 |
| Opus 5 | $0.00034 | $0.01901 |
| Sonnet 5 | $0.00014 | $0.00760 |
| Haiku 4.5 | $0.00007 | $0.00380 |
Grade A, and why
daemon-triage 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.
How it starts
The opening of the file, as written. The whole thing — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
An operator's entry point when the daemon has a feature wedged. It answers three questions, in order:
- What is the observable state? — gathered from evidence, not inferred.
- Which failure class is this? — resolved against a signal table, not a guess.
- What is the operator's next move? — the one runbook that owns this class, plus the exact commands to run.
It may then carry out that recovery — but every mutation requires the operator's explicit approval first, and approval is per-action, never blanket.
The approval contract
Diagnosis is unconditionally read-only. Everything in §1–§3 — reading state, classifying, choosing a runbook, writing the triage report — happens without asking. Gathering evidence must never change the thing being measured.
Every mutation stops and asks. Before any action that changes state —
clearing a halt, parking or unparking, editing .pipeline/, any git command
that writes, restarting the daemon — present the action, what it changes, its
blast radius, and wait for the operator to approve that specific action. Then do
it. Do not batch several mutations behind one approval, and do not treat
approval of a diagnosis as approval to act on it.
"Proceed" is not standing consent. Approval covers the action just described, once. The next mutation asks again, even if it is the obvious next step in the same recovery.
This is deliberately conservative, and deliberately temporary. Daemon recovery is where a confident wrong move costs the most, and the failure modes that hurt worst are the ones where the display is lying and the work is fine, or the halt is legitimate and clearing it just re-halts. Ask-first buys the operator a veto at exactly those moments. As classification proves reliable in practice, the safest, most reversible actions are the candidates to relax first — the destructive ones in §4 are not.
Not a substitute for the runbooks. The runbooks under runbooks/ (symlinked
into this skill directory) remain the canonical procedures. This skill exists to
pick the right one correctly and to stop an operator from guessing.
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.
- 10d ago First seen · 314 lines · 69 tokens per session scan A 2a9ade8283fd
daemon-triage is a skill published in the GitHub repository jstoup111/ai-conductor (7 stars, last pushed today), licensed Apache-2.0. It adds 69 tokens to every session and 3,801 once invoked, about $0.0003 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 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.