Borrowing it
Nothing to install: this file belongs to NanmiCoder/open-image-prompts. 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/NanmiCoder/open-image-prompts/main/AGENTS.mdgit clone --depth 1 https://github.com/NanmiCoder/open-image-promptsWrote 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/nanmicoder/open-image-prompts/agents-md)<a href="https://agentmods.dev/instructions/nanmicoder/open-image-prompts/agents-md"><img src="https://agentmods.dev/badge/instructions/nanmicoder/open-image-prompts/agents-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/nanmicoder/open-image-prompts/agents-md"><img src="https://agentmods.dev/badge/instructions/nanmicoder/open-image-prompts/agents-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 | $0.01585 | $0.01585 |
| Opus 5.5 | $0.00634 | $0.00634 |
| Sonnet 5.5 | $0.00317 | $0.00317 |
| Haiku 4.5 | $0.00159 | $0.00159 |
Grade A, and why
open-image-prompts 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 21d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for coding agents working in or starting up this repository.
What this repository is
An open, local-first visual prompt archive plus two installable Agent Skills. The application is a read-only SQLite API (Python, standard library only) behind a React/Vite frontend. Nothing here trains, labels, or writes prompt data.
Get it running
Prerequisites: Node.js 20.19+ or 22.12+, and Git. Python arrives via uv, which
start.sh installs into .oip/tools/ if it is missing.
./start.sh # macOS/Linux; Windows: start.bat
start.sh is the whole setup: it prepares Python, downloads the dataset,
installs frontend packages, and starts the API and frontend together. Open the
URL it prints, not a URL you assumed — see "Ports" below.
To skip the ~4 GB of image packs (the gallery then falls back to each record's original source URL):
OIP_FETCH_SKIP_IMAGES=1 ./start.sh
Step-by-step instead of the launcher:
uv sync --locked
npm run data:pull # or data:pull:db to skip image packs
npm --prefix web ci
npm run dev
The dataset is not in Git
A clone gives you code, Skills, taxonomy, and small indexes — not the corpus.
db/prompts.db.gz (~80 MB) and images/ (~4.2 GB across nine monthly packs)
are downloaded from GitHub Releases by scripts/fetch_dataset.py, which verifies
every asset's sha256 against data/dataset-manifest.json. Both paths are
gitignored, and re-running the fetch is safe: verified assets are skipped.
Expect this layout after a full pull:
db/prompts.db.gz # compressed archive from Releases
images/<tweet_id>/N.jpg # extracted image packs
.oip/runtime/prompts.db # expanded read-only SQLite, created on first start
.oip/packs/*.sha256 # extraction markers so unchanged packs are skipped
Search and retrieval work without the image packs. Only local image preview needs them.
Videos follow the same rule: the packs ship images and poster frames, the corpus
references 2,061 clips, and no video binary travels through Git. A <video>
whose file is missing falls back to X's CDN — unreachable from mainland China,
expiring over time — so a clone without clips shows posters only. When a task
needs playable video, pull the clips onto the machine that serves them:
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.
- 21d ago Changed · +20 lines · +262 tokens per session 0c7a6f802d98
- 2mo ago First seen · 136 lines · 1,323 tokens per session scan A 424342b75abe
open-image-prompts AGENTS.md is an instructions file published in the GitHub repository NanmiCoder/open-image-prompts (387 stars, last pushed yesterday), licensed MIT. It adds 1,585 tokens to every session, about $0.0063 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.
open-image-prompts AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| open-image-prompts AGENTS.mdNanmiCoder/open-image-prompts | Instructions file | 387 | yesterday | MIT | A | 1,585 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | 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 |