Borrowing it
Nothing to install: this file belongs to 1939869736luosi/codex-sessions-manager. 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/1939869736luosi/codex-sessions-manager/main/AGENTS.mdgit clone --depth 1 https://github.com/1939869736luosi/codex-sessions-managerWrote 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/1939869736luosi/codex-sessions-manager/agents-md)<a href="https://agentmods.dev/instructions/1939869736luosi/codex-sessions-manager/agents-md"><img src="https://agentmods.dev/badge/instructions/1939869736luosi/codex-sessions-manager/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 | $0.00343 | $0.00343 |
| Opus 5 | $0.00171 | $0.00171 |
| Sonnet 5 | $0.00069 | $0.00069 |
| Haiku 4.5 | $0.00034 | $0.00034 |
Grade A, and why
codex-sessions-manager 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 8d 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
Agent guidance
Default execution model
- Use one agent for ordinary changes.
- Three concurrent agents is a hard ceiling, not a target. Use more than one only for independent work that can be reviewed separately.
- Use one primary planning or review framework per phase. Do not stack native Plan, Superpowers, Matt Pocock workflows, and Ultra-style orchestration.
- Small fixes should use direct model reasoning and focused tests. Use a diagnosing workflow only for a difficult reproduction.
- Run one independent release review on the fixed release commit and tarball. Do not repeat heavyweight review scaffolding for every small commit.
Repository boundaries
- Prefer CLI for scripts, pipes, complete JSON, canonical event streams, and byte-exact exports.
- Keep MCP for bounded structured reads, resources/instructions, host permissions, and explicitly confirmed admin actions.
- CLI and MCP must call the same application operation. MCP must never shell out to the CLI, and no generic
run_commandtool may be added. - Read-only operations must skip unsafe paths with an explicit warning. Mutations must fail closed.
- Never add local sessions, real home paths, security advisory drafts, encrypted backups, tokens, or raw memory text to Git, Actions artifacts, fixtures, docs, or npm packages.
Required verification
- Add a failing test before changing behavior.
- For migrated operations, compare normalized CLI JSON and MCP structured results.
- Run typecheck, relevant tests, the full suite, compatibility checks, build, package-manifest checks, and production dependency audit in proportion to the change.
- A release requires first-principles, dependency-order, critical, adversarial, and independent GO/NO-GO review.
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.
- 8d ago First seen · 25 lines · 343 tokens per session scan A b7f8c13a5cf2
codex-sessions-manager AGENTS.md is an instructions file published in the GitHub repository 1939869736luosi/codex-sessions-manager (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 343 tokens to every session, about $0.0017 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
vscode buildNext.instructions.md
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).
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).
langchain AGENTS.md
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.
spec-kit AGENTS.md
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.