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/dailin521/codex-provider-sync/agents-mdgit clone --depth 1 https://github.com/Dailin521/codex-provider-syncWhat 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 | $0.01480 | $0.01480 |
| Opus 5 | $0.00740 | $0.00740 |
| Sonnet 5 | $0.00296 | $0.00296 |
| Haiku 4.5 | $0.00148 | $0.00148 |
Grade A, and why
codex-provider-sync 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 2d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI / Agent Operator Guide
This file is for AI assistants and automation working in this repository. User-facing setup and usage belong in README.md and docs/.
vNext architecture baseline
The accepted target architecture and staged migration plan is vNext Electron + Node architecture. Read it before any Electron, shared Node Core, repository restructuring, desktop replacement, or other vNext work.
It defines the target, not the current implementation. Existing code, tests, and released compatibility contracts remain authoritative until the relevant migration-stage exit criteria pass. Do not delete the .NET implementation, break the CLI/Web contract, or perform a big-bang rewrite ahead of those gates.
Phase 0 decisions and frozen behavior are indexed in the vNext migration execution index. Before changing an external behavior, read the applicable Core behavior contract, CLI contract, error-code contract, and behavior fixture catalog, plus the Accepted ADRs in docs/adr/.
An external behavior change must update its contract and add or update a fixture/test in the same PR. Target-state text is not proof that a feature exists: keep current behavior, transitional adapter behavior, and the vNext target explicitly separated.
Goal
Restore Codex session visibility after model_provider changes by keeping rollout metadata and the resolved SQLite thread index aligned. Do not treat this as an authentication or account-management tool.
Choose the interface
- Prefer the Windows GUI for users who want a double-click tool and do not want Node.js.
- Prefer the Local Web UI for browser-based or cross-platform use:
codex-provider web. - Use the CLI for explicit command requests, automation, diagnostics, WSL paths, or when a GUI is unavailable.
- Use
CodexProviderSync.Automation.exeonly for repository development or explicit Automation work. It ships with the v0.4 Windows Release, but protocol 0.4 is experimental and is not a stable public API or a production GUI control port.
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.
- 2d ago First seen · 87 lines · 1,480 tokens per session scan A e2d1e8cb6130
codex-provider-sync AGENTS.md is an instructions file published in the GitHub repository Dailin521/codex-provider-sync (3,301 stars, last pushed 4d ago), licensed MIT. It adds 1,480 tokens to every session, about $0.0074 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
codex-command-center AGENTS.md
Instructions for sevensir888/codex-command-center, a project described as: A local desktop control center for organizing Codex projects, engineering tasks, sessions, Git changes, Skills, and MCP configuration.
stealth-code CLAUDE.md
Instructions for suxrobGM/stealth-code, covering stealthcode, build & run, architecture, project structure and key conventions.
codex-third-party-subagents AGENTS.md
Instructions for dhy365-creator/codex-third-party-subagents, covering agents.md, project scope, rules for agents working here, layout and validation.
codex-token-meter AGENTS.md
Instructions for prefect12/codex-token-meter, covering ai token meter development guide, project shape, build and verification, git workflow and ai token meter test loop.
codex-loop-orchestra AGENTS.md
Instructions for LEO001020/codex-loop-orchestra, covering loop discipline, 1. decomposition discipline (single-pass plan-and-solve), 3. return convention (all subagents, mandatory), 4. recoverable compression directive and 5. kernel trigger rules (ipybox, when enabled).
dev-flow AGENTS.md
Instructions for Innocent-children/dev-flow, covering dev flow repository instructions, authority, requirement scope, documentation and internationalization and product boundary.