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/thomasnormal/codex-auto-continue/agents-mdgit clone --depth 1 https://github.com/thomasnormal/codex-auto-continueWhat 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 | $0.00655 | $0.00655 |
| Opus 5 | $0.00328 | $0.00328 |
| Sonnet 5 | $0.00131 | $0.00131 |
| Haiku 4.5 | $0.00065 | $0.00065 |
Grade A, and why
codex-auto-continue 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 today.
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 — 20 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
Core entrypoints live in bin/: auto_continue_watchd.py manages watchers and auto_continue_logwatch.py tails Codex events. Tests live in test/ with Python unit suites in test_watchd_unit.py, test_logwatch_unit.py, test_real_codex_contract.py, and test_real_codex_integration.py. test/smoke.sh and test/test_rollout_e2e.sh are the fast CLI and real-Codex integration wrappers. Architecture notes and the running engineering log live in docs/. Example prompt text lives in examples/messages/.
Build, Test, and Development Commands
Run the watcher locally with python3 bin/auto_continue_watchd.py status or python3 bin/auto_continue_watchd.py start %6 --message "continue". Use bash test/smoke.sh for fast syntax and CLI checks. Use python3 -m unittest test.test_watchd_unit test.test_logwatch_unit for isolated manager and watcher logic. Use bash test/test_rollout_e2e.sh only when tmux, codex, and valid credentials are available; it launches real-Codex tests on a private tmux socket so it does not touch the existing server.
Coding Style & Naming Conventions
Follow existing Python and shell style: 4-space indentation in Python, set -euo pipefail in shell, and small stdlib-first helpers over new dependencies. Prefer snake_case for Python functions, variables, and test names. Keep CLI output short and operator-focused. Preserve the current file naming pattern: auto_continue_*.py for runtime code and test_*.py or test_*.sh for tests.
Testing Guidelines
Prefer test-driven changes. Add or extend a unit or regression test before fixing behavior, especially for pane resolution, thread detection, completion-source health, and thread-keyed state handling. Put pure logic coverage in test/test_watchd_unit.py and test/test_logwatch_unit.py using unittest and unittest.mock. Reserve the real-Codex harness for contract and integration behavior. Name tests after the behavior under test, for example test_resolve_thread_id_fails_when_unknown.
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.
- today First seen · 20 lines · 655 tokens per session scan A 66f30db35ade
codex-auto-continue AGENTS.md is an instructions file published in the GitHub repository thomasnormal/codex-auto-continue (24 stars, last pushed 5mo ago), licensed MIT. It adds 655 tokens to every session, about $0.0033 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 2026-09-01.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.