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/nteract/semiotic/copilot-instructionsgit clone --depth 1 https://github.com/nteract/semioticWhat 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 | $0.00336 | $0.00336 |
| Opus 5 | $0.00168 | $0.00168 |
| Sonnet 5 | $0.00067 | $0.00067 |
| Haiku 4.5 | $0.00034 | $0.00034 |
Grade A, and why
semiotic copilot-instructions.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.
What it actually says
Semiotic Copilot instructions
Use AGENTS.md as the authoritative repository-wide development guide. This
short compatibility file exists for Copilot surfaces that do not yet load
AGENTS.md directly; open that file when the task needs repository layout,
commands, product contracts, or the full verification matrix.
- Semiotic is a strict TypeScript/React visualization library. Follow the double-quote, no-semicolon, Prettier, and ESLint conventions already present.
- Preserve unrelated worktree changes and make the smallest coherent change.
- Prefer high-level chart components and family subpath imports in production examples; use Stream Frames only for controls the high-level API does not expose.
- Keep public APIs, types, chart specs, schemas, generated documentation, and focused tests synchronized.
- Do not hand-edit build output or generated marker sections. Run the owning generator.
- Run checks proportional to the change and report only checks that actually completed successfully.
For chart-generation guidance, start with ai/system-prompt.md and the exact
component schema. Treat ai/reference.md and ai/examples.md as on-demand
resources rather than default context.
For pull request review, use the workflow in
.github/skills/code-review/SKILL.md. Use GitHub MCP to retrieve referenced
issues, incidents, related pull requests, and relevant CI results. Use
Playwright MCP when a review claim depends on browser rendering, interaction,
responsive layout, hydration, or accessibility. When an unstable custom lint
fails, evaluate the rule as well as the code before recommending a disposition.
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 · 31 lines · 336 tokens per session scan A 26e86158f21e
semiotic copilot-instructions.md is an instructions file published in the GitHub repository nteract/semiotic (2,691 stars, last pushed 2d ago), licensed Apache-2.0. It adds 336 tokens to every session, about $0.0017 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 instructions, from other repositories
recharts AGENTS.md
Instructions for recharts/recharts: This is Recharts repository. Recharts is a React-based charting library. The goal is to provide a simple, declarative, and composable way to build charts. We value consistency, usability, and performance. Accessibility is important.
cdc-open-viz AGENTS.md
Instructions for CDCgov/cdc-open-viz, covering ai agent instructions, branch comparison, testing commands, required test strategy and targeted tests (default).
web-vaccine-tracker CLAUDE.md
Instructions for damiansire/web-vaccine-tracker, covering claude.md — web-vaccine-tracker, estándar nivel mundial, piso legibilidad en frío (k–m), reglas del stack (citadas del corpus) and ui.
web-vaccine-tracker AGENTS.md
Instructions for damiansire/web-vaccine-tracker, covering agents.md, checklist pre-pr (numerado, en orden) and stop-signs (parar y preguntar, no improvisar).
datastoria AGENTS.md
AGENTS.md instructions for FrankChen021/datastoria, covering agents.md, repository overview, scope rules, workflow expectations and commands.
memory-visualizer CLAUDE.md
Claude Code instructions for mjherich/memory-visualizer, covering claude.md, common development commands, development server, build and preview production build.