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 skills/steipete/agent-scripts/ssh-doctornpx skills add steipete/agent-scripts --skill ssh-doctorgit clone --depth 1 https://github.com/steipete/agent-scriptsWhat 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 | $0.00023 | $0.01414 |
| Opus 5 | $0.00012 | $0.00707 |
| Sonnet 5 | $0.00005 | $0.00283 |
| Haiku 4.5 | $0.00002 | $0.00141 |
Grade B, and why
ssh-doctor scanned grade B 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 2d 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.
sudo systemsetup -getremotelogin How it starts
The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SSH Doctor
Use when SSH connects then closes before auth, Remote Login seems advertised but unusable, or local/remote Mac SSH needs diagnosis.
Rules
- Do not print secrets, tokens, full env, or broad secret grep output.
- Validate locally first: loopback failure means server-side sshd/launchd/config; loopback success plus remote failure means network/firewall/filter/listen path.
- Report suspicious config lines before changing
/etc/ssh/sshd_config. - Prefer non-interactive SSH:
ssh -o RequestTTY=no -o RemoteCommand=none HOST 'hostname; id -un'
Baseline
hostname; id -un; sw_vers
ipconfig getifaddr en0
ipconfig getifaddr en1 2>/dev/null || true
ipconfig getifaddr en7 2>/dev/null || true
sudo systemsetup -getremotelogin
sudo systemsetup -setremotelogin on
sudo launchctl print system/com.openssh.sshd 2>&1 | head -80
sudo launchctl kickstart -k system/com.openssh.sshd
sudo lsof -nP -iTCP:22 -sTCP:LISTEN
nc -vz 127.0.0.1 22
ssh -4 -F /dev/null -o RequestTTY=no -o RemoteCommand=none [email protected] 'hostname; id -un'
Use BatchMode=yes only when password fallback would hang or prompt.
Config
sudo sshd -T 2>&1 | egrep -i '^(allowusers|denyusers|allowgroups|denygroups|listenaddress|maxstartups|logingracetime|usepam|passwordauthentication|pubkeyauthentication|authenticationmethods)'
sudo egrep -n '^[[:space:]]*(AllowUsers|DenyUsers|AllowGroups|DenyGroups|Match|MaxStartups|LoginGraceTime|ListenAddress|AuthenticationMethods|UsePAM|PasswordAuthentication|PubkeyAuthentication)\b' /etc/ssh/sshd_config /etc/ssh/sshd_config.d/* 2>/dev/null || true
Suspicious:
DenyUsersmatching target user- restrictive
AllowUsers/AllowGroups Matchblock accidentally applying- tiny
MaxStartups - tiny
LoginGraceTime ListenAddressmissing target interface
Logs
sudo log show --last 30m --predicate 'process == "sshd" OR process == "launchd"' --style compact | tail -160
Important Mac symptom:
- client:
kex_exchange_identification: Connection closed by remote host - server log:
Could not create new instance of inetd service: 67: Too many processes launchctl print system/com.openssh.sshd: highcopy count- many
sshd-session: USERprocesses parented by PID 1
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.
- 2d ago First seen · 147 lines · 23 tokens per session scan B b2f5918b9c88
ssh-doctor is a skill published in the GitHub repository steipete/agent-scripts (6,590 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 1,414 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.