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/paritytech/playground-cli/agents-mdgit clone --depth 1 https://github.com/paritytech/playground-cliWhat 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 | $0.02235 | $0.02235 |
| Opus 5 | $0.01118 | $0.01118 |
| Sonnet 5 | $0.00447 | $0.00447 |
| Haiku 4.5 | $0.00224 | $0.00224 |
Grade A, and why
playground-cli 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 yesterday.
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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project Overview
playground-cli is a TypeScript ESM CLI for Polkadot Playground, installed as the playground
command (short alias pg — both invoke the same binary). The CLI uses Commander and Ink/React for
its terminal UI, is compiled with Bun, and is tested with Vitest.
CLAUDE.md is the authoritative source for repo-specific invariants and rationale. Read it
alongside this file; where the two differ, CLAUDE.md wins.
Commands
- Install dependencies:
pnpm install - Build compiled CLI:
pnpm build - Run tests:
pnpm test - Watch tests:
pnpm test:watch - Type check:
pnpm exec tsc --noEmit - Format:
pnpm format - Check formatting:
pnpm format:check - Check license headers:
pnpm lint:license - Install local binary:
pnpm cli:install
Verification before committing
Run all three before claiming work is done, opening a PR, or merging. The first two are enforced by CI; the third catches regressions:
pnpm format:check
pnpm lint:license
pnpm test
pnpm build compiles with Bun, which strips types without checking them — it is NOT a type
signal, and there is no tsc step in CI. The tree carries a known baseline of pre-existing
tsc --noEmit errors; before claiming a change complete, run
pnpm exec tsc --noEmit 2>&1 | grep -c "error TS" and confirm the count did not grow. If
lint:license flags a file you authored, run ./scripts/check-license-headers.sh --fix to prepend
the Parity Apache-2.0 block (SPDX line + Parity copyright line, both required) — every tracked
.ts / .tsx / .rs file must carry it.
Repository Conventions
- Tests live next to the source as
*.test.ts.vitest.config.tsonly picks up.test.ts; update it before adding.tsxtests. - Pure logic embedded in
.tsxcomponents should be lifted into sibling.tsfiles so tests can import it without pulling React and Ink into the runner. - Every user-facing PR needs a changeset in
.changeset/*.md. Refactors, tests, and internal tooling-only changes can skip one. - Do not add AI/tool attribution, signatures, or provenance to commits, PRs, generated files, or repo content.
- Do not commit design docs, brainstorming notes, context dumps, or scratch files.
- Do not mock
polkadot-apiprimitives such asEnumor encoders in tests. - Long-lived resources such as
TerminalAdapter, session signers, and chain clients must be explicitly destroyed in cleanups — the WebSocket keeps the event loop alive, so a forgottendestroy()manifests asplayground <cmd>hanging after the work visibly finishes.
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.
- yesterday First seen · 153 lines · 2,235 tokens per session scan A c4b5b2ae0064
playground-cli AGENTS.md is an instructions file published in the GitHub repository paritytech/playground-cli (5 stars, last pushed 11d ago), licensed Apache-2.0. It adds 2,235 tokens to every session, about $0.0112 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
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.
buildNext
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).
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.
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).
spec-kit 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.
langchain 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.