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 TasiTech/tasi-harness --skill tasi-travelgit clone --depth 1 https://github.com/TasiTech/tasi-harnessWrote 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/tasitech/tasi-harness/tasi-travel)<a href="https://agentmods.dev/skills/tasitech/tasi-harness/tasi-travel"><img src="https://agentmods.dev/badge/skills/tasitech/tasi-harness/tasi-travel/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/tasitech/tasi-harness/tasi-travel"><img src="https://agentmods.dev/badge/skills/tasitech/tasi-harness/tasi-travel.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00051 | $0.04978 |
| Opus 5 | $0.00026 | $0.02489 |
| Sonnet 5 | $0.00010 | $0.00996 |
| Haiku 4.5 | $0.00005 | $0.00498 |
Grade A, and why
tasi-travel 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 12d 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 — 428 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tasi-Travel Skill (Entry)
Purpose
Provide a single entry workflow for trip planning while keeping provider logic modular and extensible.
Architecture
This skill uses an entry-plus-modules structure:
- Entry layer (this file): request understanding, orchestration, provider routing, and output assembly.
- Provider layer: platform-specific retrieval and normalization.
- Browser evidence layer: Ctrip web retrieval through built-in
browser_*tools, with runtime mode handled by the harness. - Visualization layer: map route link generation and formatting policy (Amap URL).
- Capability details: kept inside provider docs to reduce fragmentation while preserving extension points.
Required Inputs
- user_request
- constraints:
- city_or_region
- start_date
- end_date
- traveler_count
- total_budget
- must_visit (optional)
- avoid_items (optional)
- hotel_preference (optional)
- transport_preference (optional)
- tool_capabilities: list of available tools and keys
- feedback_history (optional)
- map_render_request (optional):
- map_enabled (bool; default true)
- map_focus (day, optional; default day)
- travel_mode (car|walk|bus|bike, optional; default car)
- use_lnglat (bool, optional; default false)
Provider Configuration
Provider Priority by Capability
| Capability | Primary Provider | Secondary Provider | Fallback |
|---|---|---|---|
| Flight search | ctrip_browser | flyai | offline_estimate |
| Hotel search | ctrip_browser | flyai | offline_estimate |
| Train search | ctrip_browser | flyai | offline_estimate |
| POI discovery | ctrip_browser | flyai | offline_estimate |
| Route/Distance matrix | flyai | tencent_map | offline_estimate |
| Weather | flyai | tencent_map | offline_estimate |
Offline Fallback Definitions
offline_sketch: a fallback mechanism that fills content using alternative methods or offline/pre-generated data when dynamic services are unavailable.offline_estimate: a fallback mechanism that generates conservative approximations using heuristics, historical averages, or cached static data when online providers fail. Results must be explicitly marked with[estimated].
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/map/multi_day_map.html 4.7 KB
- references/ctrip-information-search-guide.md 2.8 KB
- references/provider-ctrip-browser.md 26 KB
- references/provider-extension.md 2.7 KB
- references/provider-flyai.md 2.5 KB
- references/provider-tencent-map.md 2.7 KB
- scripts/extract_ctrip_destinations.py 7.8 KB runs code
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.
- 12d ago First seen · 428 lines · 51 tokens per session scan A f3d990f2464d
tasi-travel is a skill published in the GitHub repository TasiTech/tasi-harness (11 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 4,978 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
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…