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 jezweb/vite-flare-starter --skill route-findinggit clone --depth 1 https://github.com/jezweb/vite-flare-starterWrote 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/jezweb/vite-flare-starter/route-finding)<a href="https://agentmods.dev/skills/jezweb/vite-flare-starter/route-finding"><img src="https://agentmods.dev/badge/skills/jezweb/vite-flare-starter/route-finding.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 | $0.00043 | $0.00664 |
| Opus 5 | $0.00022 | $0.00332 |
| Sonnet 5 | $0.00009 | $0.00133 |
| Haiku 4.5 | $0.00004 | $0.00066 |
Grade A, and why
route-finding 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Route Finding
Purpose
This skill is loaded as a SessionEnd hook by routines that emit findings. The main agent has just finished a run and produced text + tool calls. Your job is to:
- Decide which output channel(s) the finding should land in.
- Produce a one-line summary of what happened, suitable for the run history tail.
Channels you can reason about
The main agent already had access to these channel tools — so by the time this hook fires, they may have been called or skipped. Use the run text + tool calls to figure out what to do next, if anything:
- inbox_add — drop a finding into the user's Inbox for them to review later. Use when the work produced a result the user should be aware of but doesn't need to act on right now.
- notify — send a transient bell ping. Use sparingly — only for genuinely time-sensitive things ("backup failed", "deploy ready").
- approval_queue — gate a destructive action behind human review. Use when the agent wants to send an email, post publicly, modify shared data.
- space_send — post to a team Space. Use when the finding is collaborative — the team should see it together.
- webhook_post — fire an external URL. Use when the finding feeds into a tool the user has set up.
Decision rules
if (no work was done OR no result worth surfacing):
→ produce a 1-line summary saying "no findings"
else if (the agent already called a channel tool):
→ just summarise what was sent + where
else if (the work suggests destructive action — sending email, posting publicly):
→ suggest approval_queue OR notify the user via inbox_add (NOT both)
else if (the work produced an informational finding):
→ suggest inbox_add with importance set per the user's stated thresholds
else:
→ just summarise; don't dispatch — sometimes nothing is the right move
Output format
You don't actually call channel tools yourself (you're a SessionEnd hook, not the main agent). Instead, return a short paragraph the routine scheduler stores as routine_runs.outputSummary. The next fire reads the most recent K of these as context — keep them dense and useful.
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 · 60 lines · 43 tokens per session scan A 97c31d1fd93e
route-finding is a skill published in the GitHub repository jezweb/vite-flare-starter (48 stars, last pushed 13d ago), licensed MIT. It adds 43 tokens to every session and 664 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…