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 AI-Shell-Team/aish --skill dns-diagnosegit clone --depth 1 https://github.com/AI-Shell-Team/aishWrote 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/ai-shell-team/aish/dns-diagnose)<a href="https://agentmods.dev/skills/ai-shell-team/aish/dns-diagnose"><img src="https://agentmods.dev/badge/skills/ai-shell-team/aish/dns-diagnose.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00066 | $0.01219 |
| Opus 5 | $0.00033 | $0.00609 |
| Sonnet 5 | $0.00013 | $0.00244 |
| Haiku 4.5 | $0.00007 | $0.00122 |
Grade A, and why
dns-diagnose 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 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.
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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DNS resolution diagnosis
Troubleshoot domain resolution failures, wrong answers, or “I changed the record but it still fails” on this host.
Out of scope: editing /etc/resolv.conf or NetworkManager by default, buying domains / changing authoritative DNS for the user, HTTP 5xx, or TLS certificate issues (ssl-cert-toolkit). Path quality after resolve succeeds belongs to network-path-diagnose.
Rules
- Need a domain first: ask if missing; optional expected type (A/AAAA/CNAME/MX/TXT).
- Read-only: inspect resolution and config; do not change DNS servers or hosts unless the user explicitly asks (default is advice only).
- Stop when enough: once you can separate “local resolver” vs “authoritative/record” issues, answer.
- Missing tools: prefer
dig; elsehost/nslookup/getent. - Ask before sending internal/sensitive names to public DNS,
+trace, orwhois.
Workflow
Confirm domain & symptom → local resolver → local dig → optional external checks → answer
1. Confirm inputs
| Input | Notes |
|---|---|
| Domain | e.g. example.com or www.example.com |
| Symptom | total failure / wrong answer / recent change not visible / only on some networks |
| Record type | default A/AAAA; include MX if mail-related |
2. Local resolver
cat /etc/resolv.conf 2>/dev/null
resolvectl status 2>/dev/null || systemd-resolve --status 2>/dev/null || true
getent ahosts <domain> | head -10
grep '^hosts:' /etc/nsswitch.conf 2>/dev/null
grep -E "^\s*[0-9a-fA-F:.]+\s+.*\b<domain>\b" /etc/hosts 2>/dev/null || true
| Observation | Lean toward |
|---|---|
getent works, browser fails |
App/proxy/DoH; not only system DNS |
Bad /etc/hosts entry |
Local hijack |
| No nameserver / broken resolved | Local resolver config |
3. Local dig (default)
command -v dig
dig +noall +answer +stats <domain> A
dig +noall +answer <domain> AAAA
Without dig: host <domain> or nslookup <domain>.
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 · 153 lines · 66 tokens per session scan A f3a61ba15f3c
dns-diagnose is a skill published in the GitHub repository AI-Shell-Team/aish (532 stars, last pushed today), licensed Apache-2.0. It adds 66 tokens to every session and 1,219 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 2026-08-30.
Other skills, from other repositories
completion-script-generator
Generates shell completion scripts for CLI tools. Parses command structure from help output, commander/yargs configs, or manual specification. Produces completions for bash, zsh, and fish that follow each shell's conventions.
ondb
A logical analysis and reasoning tool for AI. Use when decomposing documents into structured knowledge, querying entities and relations, validating consistency, or indexing files. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", "analyze this document", entity CRUD, or cross-skill…
naming
Naming framework for x-cmd modules / commands / subcommands. Subjective + scenario-driven; the skill is a thin shell, NOT a rulebook. Three layers: investigate (goal), naming. .yml (OKR + session record, a .rule file), naming.okr-creator.yml (meta-rule that audits the session).
skill0-writer
Writing conventions for skill0 documents — pyramid structure, line limits, and layout rules.
ccal
Chinese Calendar with Lunar-Solar Conversion.
score
Weighted dimension scoring framework for AI agents — "Don't guess. Score." Core idea: understand needs first, draft then iterate, the agent is the analyst. Outputs ranked TSV via x score compute.