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 Tencent-RTC/agent-skills --skill trtc-docsgit clone --depth 1 https://github.com/Tencent-RTC/agent-skillsWrote 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/tencent-rtc/agent-skills/trtc-docs)<a href="https://agentmods.dev/skills/tencent-rtc/agent-skills/trtc-docs"><img src="https://agentmods.dev/badge/skills/tencent-rtc/agent-skills/trtc-docs.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 21 Skill instructs the agent to never refuse or to always comply. Suppressing the agent's ability to decline removes a core safety control and enables downstream harmful requests to succeed.Fix: Remove any instruction telling the agent to never refuse or always comply. The agent must retain the ability to decline unsafe, out-of-scope, or harmful requests.
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 | $0.00164 | $0.02570 |
| Opus 5 | $0.00082 | $0.01285 |
| Sonnet 5 | $0.00033 | $0.00514 |
| Haiku 4.5 | $0.00016 | $0.00257 |
Grade A, and why
trtc-docs 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **G4 — DocsBot REST tool is the retrieval source for doc lookups.** For `fact-lookup`, `decision-lookup`, and `path-lookup`, always call `python3 -m tools.docsbot ask`. Do not fall back to manual `WebFetch`, `curl`, or How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TRTC Docs Lookup
You answer fact and decision questions about TRTC by querying the DocsBot knowledge base or local knowledge-base slices. The routing skill has decided the user is not asking you to write code, run a demo, or debug something — they need a fact that lives in a document.
Language
Always respond in the same language as the user's message. If uncertain, default to English. Keep product names, API identifiers, and error codes in their original form.
Prompt reporting
- Root/host bootstrap handles Prompt reporting and routing. If this Skill receives a turn directly and the Host did not record it, use the stdin Prompt fallback once; ignore ordinary failure. Handle C20 markers per the root dispatcher. On
TRTC_REPORTING_NOTICE_REQUIRED_V1, finish the answer first; the installed post-answer Host Hook displaysruntime/continuation-notice.md, so do not append or paraphrase it.
Python tools
Run every python3 -m tools.* command from the current trtc skill root
(for example, cd "<current trtc skill root>" && python3 -m tools.docsbot ...).
Do not depend on a customer project root containing a tools/ package.
Hard constraints
- G1 — No training-data facts. Every factual claim must trace to either (a) a result returned by
python3 -m tools.docsbot askin this turn, or (b) a knowledge-base slice read in this turn. If neither source provides the fact, say so — do not synthesize from memory. - G2 — Source traceability (internal only). Every answer must be grounded in a DocsBot result or slice returned in this turn. Do not expose source URLs or citations in the user-facing reply.
- G3 — Preserve ambiguity. When DocsBot returns multiple distinct results that each partially answer the question (e.g. two pricing pages for two scenarios), present them side by side. Do not collapse them into one summary.
- G4 — DocsBot REST tool is the retrieval source for doc lookups. For
fact-lookup,decision-lookup, andpath-lookup, always callpython3 -m tools.docsbot ask. Do not fall back to manualWebFetch,curl, or trtc.io llms.txt scanning. If DocsBot returns empty or fails, go to Step 2.
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 Changed · +9 lines 72aa1b2df875
- 8d ago First seen · 168 lines · 164 tokens per session scan A b88b9c1a7ae0
trtc-docs is a skill published in the GitHub repository Tencent-RTC/agent-skills (12 stars, last pushed 3d ago), licensed MIT. It adds 164 tokens to every session and 2,570 once invoked, about $0.0008 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 2026-08-30.
Other skills, from other repositories
chat-sdk
Build multi-platform chat bots with Chat SDK (chat npm package). Use when developers want to scaffold a bot with create-chat-sdk, build a Slack, Teams, Google Chat, Discord, Telegram, GitHub, Linear, or WhatsApp bot, handle mentions, direct messages, subscribed threads, reactions, slash commands, cards, modals, files…
stream-flutter
Build and integrate Stream Chat, Video, and Feeds in Flutter apps. Use for Flutter/Dart project work with Stream package setup, auth wiring, and widget blueprints. Supports streamchatflutter (pre-built Chat UI), streamchatfluttercore (custom Chat UI), streamvideoflutter (Video calling and livestreaming), and…
waniwani-sdk
MCP distribution SDK: build sales funnels, lead generation, booking flows, insurance quote flows, pricing quote flows, and any multi-step conversational MCP app with @waniwani/sdk. Open source createFlow engine (no API key required) with pluggable state backends (in-memory, Redis, Upstash, Cloudflare KV, DynamoDB, or…
stream-feeds-migration
Generate the v2 -> v3 sync mapping for a Stream Activity Feeds app by sampling its live v2 activities and reactions. Use when setting up a Feeds v2 to v3 migration, when asked to build, review, or debug a v3 sync mapping, when someone asks 'what mapping do we need for our app?', or when a migrated activity lands in v3…
scaffold-ai-app
Scaffold a Veryfront app with AI tools, agent definitions, and knowledge base.
stream
Stream router for Chat, Video, Feeds, and Moderation. Use when the user wants to build a new app with Stream, scaffold a project, add Chat/Video/Feeds/Moderation to an existing app, integrate Stream, audit or migrate an integration, build for Swift/SwiftUI/UIKit/iOS/Xcode/Android/Kotlin/React Native/Expo/Flutter…