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/trtmn/agent-plugins/preflight-checknpx skills add trtmn/agent-plugins --skill preflight-checkgit clone --depth 1 https://github.com/trtmn/agent-pluginsWhat 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 | $0.00143 | $0.01027 |
| Opus 5 | $0.00072 | $0.00513 |
| Sonnet 5 | $0.00029 | $0.00205 |
| Haiku 4.5 | $0.00014 | $0.00103 |
Grade A, and why
preflight-check scanned grade A 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
import urllib.request How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preflight Connection Validator
Validate external service connections and report a clear status table before proceeding with work.
Why this exists
Nothing wastes more time than getting halfway through a task only to discover an API key expired or an MCP server is down. This skill front-loads that pain — check everything first, fix what's broken, then start real work with confidence.
Services to validate
Check each of these in order. For each service, make the minimal request that proves authentication works.
1. GitHub (gh CLI)
Run gh auth status via Bash. Look for the "Logged in" confirmation line. Extract:
- Account name
- Active scopes
- Auth method (keyring, token, etc.)
If it fails, suggest gh auth login.
2. Atlassian (MCP server)
Call mcp__claude_ai_Atlassian__atlassianUserInfo with no parameters. If it returns user info (name, email, account_id), the MCP connection and OAuth are working. Extract:
- User name
- Account status
If it fails, the MCP server may not be running or the OAuth token may have expired. Tell the user to check their MCP server configuration or re-authenticate.
3. UniFi (API key)
Load UNIFI_API_KEY from the environment. The key should be available as an environment variable. Make a request to the UniFi controller to verify the key works:
import urllib.request
import ssl
import os
import json
key = os.environ.get("UNIFI_API_KEY", "")
if not key:
print("MISSING: UNIFI_API_KEY not set")
else:
ctx = ssl._create_unverified_context()
req = urllib.request.Request(
"https://192.168.1.1/proxy/network/integration/v1/sites",
headers={"X-API-KEY": key, "Accept": "application/json"}
)
try:
resp = urllib.request.urlopen(req, context=ctx, timeout=10)
data = json.loads(resp.read())
print(f"OK: {len(data.get('data', []))} site(s) found")
except Exception as e:
print(f"FAILED: {e}")
If UNIFI_API_KEY is not in the environment, check for a .env file in the project root and load it with python-dotenv. Never try to cat or source the .env directly — it may be a 1Password FIFO pipe.
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.
- yesterday First seen · 101 lines · 143 tokens per session scan A d7e79f4cd579
preflight-check is a skill published in the GitHub repository trtmn/agent-plugins (2 stars, last pushed 5d ago), licensed Unlicense. It adds 143 tokens to every session and 1,027 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.