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/opsyhq/opsy/agents-mdgit clone --depth 1 https://github.com/opsyhq/opsyWhat 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 | $0.00431 | $0.00431 |
| Opus 5 | $0.00216 | $0.00216 |
| Sonnet 5 | $0.00086 | $0.00086 |
| Haiku 4.5 | $0.00043 | $0.00043 |
Grade A, and why
opsy 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 3d 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.
What it actually says
Agent Instructions
- Do not alter product behavior with hard-coded hacks, static semantic maps, aliases, fallbacks, or one-off exceptions.
- Keep behavior dynamic: use source-of-truth data, runtime discovery, provider APIs, database state, schemas, tools, and explicit configuration.
- If something is wrong, improve the dynamic path instead of baking the answer into code.
- Do not extract trivial one-line transformations, predicates, key builders, or field reshaping into standalone helpers. Inline them where used unless they encode a real reusable domain concept or remove meaningful duplication.
- Do not invent local wrapper types, copied API shapes, semantic aliases, or ownership structures when an existing schema, provider, contract, DB row type, or exported domain type can be reused. Prefer tightening the existing source-of-truth type over adding a parallel one.
- Prefer direct functional data flow over mutable assembly. Treat clusters of
let, broad casts,Awaited<ReturnType<...>>, and "prepare/derive" scaffolding as smells to simplify unless the code genuinely needs staged ownership. - Domain flow must be owned by one public service function. Do not hide branching domain behavior behind vague orchestration helpers named
ensure*,hydrate*,prepare*,resolve*, or similar. If a flow is "read, if missing or stale then generate/sync/upsert, then read again", write that sequence directly in the owning function. - Do not duplicate validation across route, service, workflow, and step boundaries. Put validation at the earliest boundary that owns the decision, pass typed state forward, and let downstream code handle only real source-of-truth races or failures instead of re-running the same validation.
- For database schema changes, use the repo migration workflow. Generate migrations with the package script (for API:
bun run db:generate --name <name>fromapps/api) and apply them with the package migrate script (for API:bun run db:migratefromapps/api). Do not hand-roll structural DDL; only add explicit data backfills/rewrites that the generator cannot infer.
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.
- 3d ago First seen · 12 lines · 431 tokens per session scan A 2453599ff2ae
opsy AGENTS.md is an instructions file published in the GitHub repository opsyhq/opsy (23 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 431 tokens to every session, about $0.0022 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
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.