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 instructions/resciencelab/tryskills/agents-mdgit clone --depth 1 https://github.com/ReScienceLab/TrySkillsWhat 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 | $0.01375 | $0.01375 |
| Opus 5 | $0.00687 | $0.00687 |
| Sonnet 5 | $0.00275 | $0.00275 |
| Haiku 4.5 | $0.00137 | $0.00137 |
Grade A, and why
TrySkills AGENTS.md 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 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.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- TrySkills CLAUDE.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TrySkills.sh
An open-source platform where users can instantly try any AI agent skill in a sandboxed environment. Built with Next.js 16, Convex, Clerk, and Daytona sandboxes.
Core Commands
- Dev server:
bun dev - Build:
bun run build - Lint:
bun run lint - Test:
bun run test(ornpx vitest run) - Type check:
npx tsc --noEmit - Convex dev:
npx convex dev --once - Convex prod deploy:
npx convex deploy --yes
Always run type check + tests before committing.
Project Layout
├── convex/ → Convex backend (schema, mutations, queries, crons)
├── src/
│ ├── app/ → Next.js App Router pages
│ │ ├── [...skillPath]/ → Skill page (launch + inline chat)
│ │ ├── api/hermes/ → Server-side proxy for Hermes Gateway API
│ │ ├── api/sandbox/ → Sandbox info + heartbeat API
│ │ ├── dashboard/ → User dashboard (sandbox + skill trials)
│ │ └── settings/ → API key settings
│ ├── components/
│ │ ├── chat/ → ChatPanel, useChat hook
│ │ └── ... → ConfigPanel, LaunchProgress, etc.
│ ├── hooks/ → useKeyStore, useHeartbeat
│ └── lib/
│ ├── sandbox/ → daytona.ts, hermes-api.ts, types.ts
│ ├── skill/ → resolver, parser, url-parser
│ └── providers/ → LLM provider registry
├── scripts/ → Build scripts (snapshot, etc.)
└── public/ → Static assets
Architecture
Single Sandbox Per User
Each user gets one persistent Hermes agent sandbox (Daytona). Skills accumulate on disk without cleanup. Hermes loads the requested skill per chat session.
Pool States
active— sandbox running, accepting skill installscreating— cold create in progress (exclusive lock viaacquireCreateLock)stopped— Daytona auto-stopped after 30min idle
Launch Paths
- Instant (~0ms): skill installed + config match + URL fresh + heartbeat recent → use stored URL
- Install (~3-5s): upload skill files to running sandbox, get fresh signed URL
- Cold create (~15-30s): create new Daytona sandbox from snapshot
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 First seen · 113 lines · 1,375 tokens per session scan A d88cff18adb8
TrySkills AGENTS.md is an instructions file published in the GitHub repository ReScienceLab/TrySkills (2 stars, last pushed 3mo ago), licensed MIT. It adds 1,375 tokens to every session, about $0.0069 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.