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 quinnsprouse/routecraft --skill coregit clone --depth 1 https://github.com/quinnsprouse/routecraftWrote 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/quinnsprouse/routecraft/core)<a href="https://agentmods.dev/skills/quinnsprouse/routecraft/core"><img src="https://agentmods.dev/badge/skills/quinnsprouse/routecraft/core/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/quinnsprouse/routecraft/core"><img src="https://agentmods.dev/badge/skills/quinnsprouse/routecraft/core.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00026 | $0.01469 |
| Opus 5 | $0.00013 | $0.00734 |
| Sonnet 5 | $0.00005 | $0.00294 |
| Haiku 4.5 | $0.00003 | $0.00147 |
Grade A, and why
routecraft-core 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Routecraft core
Routecraft shows connected roads and paths with source evidence. You choose each segment and keep an exact revision history.
Route rules
Every exported segment must come from an explicit route append, route edit, or named route draw command.
Never insert an unnamed connector.
route choices returns connected options. It does not generate a route.
Do not claim that a road is safe. Report the available evidence and each unknown value.
Do not treat a missing access, surface, or traffic value as permission.
Start
routecraft guide next --json
guide next returns result.actions. Follow the first applicable action. Execute its invoke value when present.
Normal commands return result.nextActions when a next step exists. Follow that action before you call guide next again.
Run guide next again only when no next action is available or you need stage guidance.
Load an exact command contract before you need more options.
routecraft guide command route.append --json
routecraft guide topic network --json
The network guide includes a local demo. Run result.bundledDemo.invoke.cli or result.bundledDemo.invoke.mcp without changing its path.
References
@rNidentifies an immutable route revision.@sNidentifies a directed network segment.@jNidentifies a junction.@eNidentifies one segment occurrence in a route.@c...identifies a hand-drawn segment.@v...identifies a hand-drawn virtual junction.
Short references stay stable inside the loaded network snapshot.
Build loop
Request connected decision legs.
routecraft route choices @r1 --unit leg --hops 1 --limit 24 --max-output 12kb --json
A leg stops at a branch, dead end, cycle, evidence change, or command bound. It keeps every exact segmentRefs value.
Inspect only choices that need more evidence.
routecraft segment get @s12 --view full --json
routecraft segment assess @s12 --profile gravel-50mm --json
routecraft segment enrich @s12 --elevation --json
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 · 167 lines · 26 tokens per session scan A 38304c9118b1
routecraft-core is a skill published in the GitHub repository quinnsprouse/routecraft (0 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 1,469 once invoked, about $0.0001 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
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.