What is agent_session_manager AGENTS.md?

Repository-specific instructions for the agent_session_manager project, a software library that coordinates command execution and provider sessions. They describe its folders, execution layers, dependency sources, and required documentation alignment.

Use them when modifying, testing, documenting, or resolving dependencies in the agent_session_manager repository.

They reduce the chance of exposing internal interfaces, choosing the wrong dependency source, or making changes that conflict with the project's architecture. They also clarify which generated files and dependencies should not be changed.

How nshkrdotcom/agent_session_manager configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to nshkrdotcom/agent_session_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.

Copy the file

curl -O https://raw.githubusercontent.com/nshkrdotcom/agent_session_manager/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/nshkrdotcom/agent_session_manager

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/nshkrdotcom/agent_session_manager/agents-md/github.svg)](https://agentmods.dev/instructions/nshkrdotcom/agent_session_manager/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/nshkrdotcom/agent_session_manager/agents-md"><img src="https://agentmods.dev/badge/instructions/nshkrdotcom/agent_session_manager/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/nshkrdotcom/agent_session_manager/agents-md"><img src="https://agentmods.dev/badge/instructions/nshkrdotcom/agent_session_manager/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 688 This file is loaded in full into every session.

When invoked 688 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00688	$0.00688
Opus 5.5	$0.00275	$0.00275
Sonnet 5.5	$0.00138	$0.00138
Haiku 4.5	$0.00069	$0.00069

Measured 2mo ago against content hash 520f57f2b4da, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent_session_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 2mo 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.

AGENTS.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure

lib/ contains public ASM modules and provider/session orchestration internals.
test/ contains ExUnit coverage and optional SDK stubs.
guides/, examples/, README.md, and CHANGELOG.md must stay aligned with runtime and dependency behavior.
doc/ is generated output and should not be edited.

Execution Plane Stack

ASM sits above cli_subprocess_core and provider SDKs; do not expose raw ExecutionPlane.* transport internals as public API.
Use CliSubprocessCore facades and mapped ASM envelopes for execution surfaces, transport errors, recovery, and events.
Committed dependency tuples remain ordinary Hex requirements so standalone clones and published consumers work without workspace tooling. Managed development loads the MWO bootstrap and obtains eligible local/GitHub/Hex coordinates from Portfolio Registry; source preferences live in operator configuration, never this repository.
MWO's process-scoped bootstrap pointer is the only dependency-management environment input read by mix.exs.
This repo is not a Weld consumer in this pass and must not receive a blind Weld dependency. Weld verification is limited to discovered Weld consumers.
Runtime application code under lib/** must not call direct OS env APIs such as System.get_env, System.fetch_env, System.put_env, or System.delete_env.
Runtime and deployment env reads belong in config/runtime.exs or an explicit Config.Provider; runtime modules read materialized values through ASM.Env or explicit caller options.

Gates

Run mix format.
Run mix compile --warnings-as-errors.
Run mix test.
Run mix credo --strict.
Run mix dialyzer.
Run mix docs --warnings-as-errors.

Live Provider Checks

For live provider checks, use ~/scripts/with_bash_secrets <command>. It sources ~/.bash/bash_secrets and execs the command. Do not print secret values. Pipe LINEAR_API_KEY via stdin for Linear examples. GitHub live examples use gh auth or GH_TOKEN/GITHUB_TOKEN from the wrapper. Codex SDK examples use the existing Codex/OpenAI machine auth through the wrapper. Live provider smoke is not product acceptance unless it runs the product-owned Extravaganza command path.

Read the full file on GitHub · 58 lines

Changes

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.

2mo ago Changed · -1 lines · -3 tokens per session 520f57f2b4da
2mo ago First seen · 59 lines · 691 tokens per session scan A ba56fb76fed8

Subscribe to this mod's changes

agent_session_manager AGENTS.md is an instructions file published in the GitHub repository nshkrdotcom/agent_session_manager (11 stars, last pushed 10d ago), licensed MIT. It adds 688 tokens to every session, about $0.0028 per session on Opus 5.5. 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.

agent ai ai-agents beam chatbot context-management

agent_session_manager AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agent_session_manager AGENTS.mdnshkrdotcom/agent_session_manager	Instructions file	11	10d ago	MIT	A	688	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

agent_session_manager: Instructions file for Codex