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/shixinnt/codex-image-context-runtime/agents-mdgit clone --depth 1 https://github.com/shixinnt/codex-image-context-runtimeWhat 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 | $0.00286 | $0.00286 |
| Opus 5 | $0.00143 | $0.00143 |
| Sonnet 5 | $0.00057 | $0.00057 |
| Haiku 4.5 | $0.00029 | $0.00029 |
Grade A, and why
codex-image-context-runtime 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
AGENTS.md
This repository is the public, image-only Image Context Runtime for Codex.
Public boundary
- Do not add personal names, email addresses, machine-specific user paths, private project identifiers, production media, credentials, Provider responses, or copied private Git history.
- Use generic fixtures created at test time.
- Keep video generation and domain-specific governance out of v0.1.
- Keep all default tests offline and free of paid Provider calls.
Runtime contract
- Provider-returned media bytes remain behind the public MCP boundary.
- Public MCP content blocks are text-only; compact structured JSON is allowed.
- Public results are capped at 32 KiB of UTF-8 serialized JSON.
- Handoffs are capped at 16 KiB of UTF-8 text.
- Public results must not contain data URLs, base64 media, binary values, absolute paths, API keys, authorization headers, raw Provider responses, or plaintext idempotency keys.
- Tool callers cannot configure new workspace roots.
Changes
- Update tests whenever the public tool catalog changes.
- Run npm test, npm run benchmark:verify, and npm run check:privacy.
- Do not describe the synthetic payload benchmark as a Codex token, latency, memory, or native-image benchmark.
- Do not claim that Codex can never slow down.
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 · 27 lines · 286 tokens per session scan A d0ad584a243d
codex-image-context-runtime AGENTS.md is an instructions file published in the GitHub repository shixinnt/codex-image-context-runtime (100 stars, last pushed 18d ago), licensed Apache-2.0. It adds 286 tokens to every session, about $0.0014 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
ima2-gen AGENTS.md
Instructions for lidge-jun/ima2-gen, covering ima2-gen — ai context, what this project does, tech stack, project structure and agent skills (packaged).
rag-rat AGENTS.md
Instructions for cq27-dev/rag-rat, covering agents.md, prefer the rag-rat mcp for code browsing, record durable learnings as rag-rat memories, repo orientation and worktree correctness.
blz AGENTS.md
Instructions for outfitter-dev/blz, covering blz repository instructions for ai agents, important, working memory, use blz and 🚀 quick start for agents.
NanoBananaMCP CLAUDE.md
Claude Code instructions for AceDataCloud/NanoBananaMCP, covering nanobananamcp, project structure, sync from docs and development.
comfyui_mcp AGENTS.md
Instructions for hybridindie/comfyui_mcp, covering agents.md, independent & harness-agnostic, project overview, tech stack and project structure.
MCP-memento copilot-instructions.md
Instructions for caiowilson/MCP-memento, covering mcp tooling policy (vs code), project architecture (big picture), critical workflows, project-specific conventions and tool notes.