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/syh1906/openai-compatible-imagegen/agents-mdgit clone --depth 1 https://github.com/Syh1906/openai-compatible-imagegenWrote 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/syh1906/openai-compatible-imagegen/agents-md)<a href="https://agentmods.dev/instructions/syh1906/openai-compatible-imagegen/agents-md"><img src="https://agentmods.dev/badge/instructions/syh1906/openai-compatible-imagegen/agents-md.svg" alt="Measured on agentmods" 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 | $0.01225 | $0.01225 |
| Opus 5 | $0.00613 | $0.00613 |
| Sonnet 5 | $0.00245 | $0.00245 |
| Haiku 4.5 | $0.00122 | $0.00122 |
Grade A, and why
openai-compatible-imagegen 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 6d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
Project Scope
OpenAI-Compatible Imagesmaintains the Standalone Skill and Codex App Plugin from one repository.- Shared image logic lives in
scripts/; each distribution uses its own adapter without duplicating the shared implementation. - The Codex Plugin consists of
skills/,mcp/,web/,.mcp.json,.codex-plugin/plugin.json, and the prebuiltdist/directory. - Track
dist/in Git. Update it only throughnpm run build; do not edit it by hand.
Package Management
- Use npm with
package-lock.jsonfor Node dependencies. - Use Python 3.12. Production Python code uses only the standard library.
- Do not install global packages or modify user-level
PATH, registry entries, or Codex configuration.
Checks
| Task | Command |
|---|---|
| Smart regression | npm test or npm run test:smart |
| Full release regression | npm run test:release |
| One test suite | npm run test:suite -- <suite> |
| One Node test file | node --test tests/<suite>/<file>.mjs |
| One Python test file | python -m unittest discover -s tests/<suite> -p <file>.py |
| Build the Plugin | npm run build |
| Check the Plugin | npm run check |
| Compile Python files | python -m compileall -q scripts |
| Check diffs | git diff --check |
Module Boundaries
scripts/: authentication, image requests, response validation, post-processing, delivery, and QA; independent of Codex, MCP, and the widget.mcp/: tool schemas, project binding, artifact storage, and runtime calls; does not construct provider image requests.web/: result cards and the focused canvas; does not read credentials or connect directly to image services.skills/openai-compatible-imagegen/: Plugin runtime tool selection and parameter decisions.- Root
SKILL.mdandreferences/: Standalone runtime contract. .agents/plugins/marketplace.json: Git marketplace entry; Plugin sources must follow the marketplace checkout..codex-plugin/plugin.json,package.json, andpackage-lock.json: keep package identity and version aligned.
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.
- 6d ago First seen · 80 lines · 1,225 tokens per session scan A 475b8688af75
openai-compatible-imagegen AGENTS.md is an instructions file published in the GitHub repository Syh1906/openai-compatible-imagegen (44 stars, last pushed 11d ago), licensed MIT. It adds 1,225 tokens to every session, about $0.0061 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
comfyui_mcp AGENTS.md
AGENTS.md instructions for hybridindie/comfyui_mcp, covering agents.md, independent & harness-agnostic, project overview, tech stack and project structure.
fal-mcp-server CLAUDE.md
Claude Code instructions for luminarylane/fal-mcp-server, covering claude.md, commands, testing, run tests and run tests with async support.
stfu AGENTS.md
Instructions for ofabiodev/stfu: Keep responses direct, concise, and focused on the requested result.
media-mcp CLAUDE.md
Claude Code instructions for lukaskellerstein/media-mcp, covering important, development workflow (code quality), before writing code, while writing code and after writing code.
sentry-instrumentation AGENTS.md
Instructions for tortastudios/sentry-instrumentation, covering agents guide — sentry-instrumentation, what this repo is, this repo has no "skill registry", if you're a codex agent asked to install this skill and skill-enable block (copy into consumer agents.md).
AmbyKit CLAUDE.md
Claude Code instructions for ambystechcom/AmbyKit, covering claude code — notes for the ambykit repo and claude-specific.