Borrowing it
Nothing to install: this file belongs to opsyhq/opsy. 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/opsyhq/opsy/main/CLAUDE.mdgit clone --depth 1 https://github.com/opsyhq/opsyWrote 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/opsyhq/opsy/claude-md)<a href="https://agentmods.dev/instructions/opsyhq/opsy/claude-md"><img src="https://agentmods.dev/badge/instructions/opsyhq/opsy/claude-md/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/opsyhq/opsy/claude-md"><img src="https://agentmods.dev/badge/instructions/opsyhq/opsy/claude-md.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 | $0.00404 | $0.00404 |
| Opus 5.5 | $0.00162 | $0.00162 |
| Sonnet 5.5 | $0.00081 | $0.00081 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
opsy CLAUDE.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 2mo 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
Claude Instructions
The idea of AGENTS.md, distilled — see it for the full rationale. Two failure modes drive everything below: baked-in answers and drift (parallel sources of truth that look equivalent today and diverge tomorrow).
-
Dynamic behavior. No hard-coded hacks, static maps, aliases, fallbacks, or one-off exceptions to steer product behavior. It comes from source-of-truth: runtime discovery, provider APIs, DB state, schemas, tools, config. If something is wrong, fix the dynamic path — never bake the answer in.
-
One source of truth. Don't invent wrapper types, copied API shapes, or parallel ownership when an existing schema/contract/DB row/domain type fits — tighten the existing type instead. Don't re-run the same validation across route/service/workflow/step; validate once at the boundary that owns the decision and pass typed state forward.
-
Minimal structure. Don't extract trivial transforms, predicates, or key builders into helpers unless they encode a real reusable concept or remove meaningful duplication — otherwise inline them. Prefer direct functional flow; treat
letclusters, broad casts,Awaited<ReturnType<…>>, and prepare/derive scaffolding as smells. -
Flow ownership. One public function owns a domain flow. Don't hide branching behind vague orchestration (
ensure*,hydrate*,prepare*,resolve*). If it's "read, if missing or stale generate/sync, read again," write that sequence directly in the owning function. -
Migrations. Generate with
bun run db:generate --name <name>fromapps/api; apply withbun run db:migratefromapps/api. No hand-rolled structural DDL — only data backfills the generator can't 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.
- 2mo ago First seen · 33 lines · 404 tokens per session scan A bcbd5fd28bf6
opsy CLAUDE.md is an instructions file published in the GitHub repository opsyhq/opsy (24 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 404 tokens to every session, about $0.0016 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.
opsy CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| opsy CLAUDE.mdopsyhq/opsy | Instructions file | 24 | 4mo ago | Apache-2.0 | A | 404 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |