Borrowing it
Nothing to install: this file belongs to jnPiyush/AgentX. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jnPiyush/AgentX/master/.github/instructions/ai.instructions.mdgit clone --depth 1 https://github.com/jnPiyush/AgentXWrote 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/instructions/jnpiyush/agentx/ai)<a href="https://agentmods.dev/instructions/jnpiyush/agentx/ai"><img src="https://agentmods.dev/badge/instructions/jnpiyush/agentx/ai/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/instructions/jnpiyush/agentx/ai"><img src="https://agentmods.dev/badge/instructions/jnpiyush/agentx/ai.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00627 | $0.00627 |
| Opus 5.5 | $0.00251 | $0.00251 |
| Sonnet 5.5 | $0.00125 | $0.00125 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
AgentX ai.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 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI & Agent Development Instructions
Auto-loads when editing agent/LLM/workflow files. For comprehensive standards, load the skill.
Skill: .github/skills/ai-systems/ai-agent-development/SKILL.md
Pre-edit gate
Apply artifact/action applicability first: only create/update/delete/rename of PRD, TechSpec, code or unit tests requires a loop before the first covered mutation. Agent/skill declarations, instructions, docs, config, plans and research/read/review-only/check/commit-only work are exempt; executable protected runtime/hook/policy code is covered. Roles and AI/workflow keywords do not decide applicability. Review fixes trigger the gate before a covered edit; review-only work inspects scoped evidence without its own loop or unrelated active state. Delegates MUST NOT start/reset/iterate/complete the assigned parent loop. Follow AGENT-PROTOCOL.md for the loop, council, plan, capture and final independent-review gates; inspect real state before claiming completion.
Key Rules
- Never hardcode API keys, endpoints, or model names -- use env vars
- Use
.envfor local dev (always in.gitignore), Key Vault or managed identity in prod - Always define response schemas for LLM calls (Pydantic / record types)
- Implement retry with exponential backoff for all model API calls
- Set explicit timeouts on all model invocations
- Handle rate limits (HTTP 429) with backoff
- Enable OpenTelemetry tracing for agent operations
- Log: prompt tokens, completion tokens, latency, model name
- Keep system prompts in separate files, not inline strings
- Version control all prompts alongside code
- Resolve available models, tool support and context/output limits from the active host. Pin a provider-supported snapshot when available; otherwise record the alias, resolved model and host version. Never invent a dated model identifier.
- Evaluate primary and configured fallback models on representative held-out tasks; document unavailable providers rather than claiming unexecuted comparisons.
- MUST run evaluation baselines before any model change
- Mock model calls in unit tests -- never call live APIs in CI
- Validate and sanitize all user inputs before sending to models
- Review OWASP AI Top 10 for threat modeling
- Quality precedes cost: reserve output/tool headroom, account for retries and delegation, and keep unknown prices/usage distinct from zero. Use token-optimizer on demand.
- Request concise evidence and conclusions, not hidden reasoning transcripts.
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 Changed · +7 lines · +109 tokens per session 4f9b646fb1c0
- 28d ago Changed · +1 tokens per session ff8ca6c04b36
- 1mo ago Changed · -1 tokens per session 1fbf6cd636c6
- 1mo ago Changed · -2 lines · -289 tokens per session becb474795ec
- 1mo ago First seen · 45 lines · 807 tokens per session scan A f55eeab69e17
AgentX ai.instructions.md is an instructions file published in the GitHub repository jnPiyush/AgentX (17 stars, last pushed 2d ago), licensed Apache-2.0. It adds 627 tokens to every session, about $0.0025 per session on Opus 5.5. 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
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).
next.js AGENTS.md
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, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.