What is shared-workspace-mcp AGENTS.md?

An AGENTS.md instruction file that defines how coding agents should work in a shared workspace, including when to decide, when to ask, and what actions require approval.

It is for controlling agent workflow, autonomy, safety checks, and decision-making in the shared-workspace-mcp repository.

It gives agents a clear operating agreement, especially for changes that could break systems, expose security risks, or delete data.

How WhileTrueBlackObelizk/shared-workspace-mcp configures Codex and Op

Reuse

Borrowing it

Nothing to install: this file belongs to WhileTrueBlackObelizk/shared-workspace-mcp. 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/WhileTrueBlackObelizk/shared-workspace-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/WhileTrueBlackObelizk/shared-workspace-mcp

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/whiletrueblackobelizk/shared-workspace-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/whiletrueblackobelizk/shared-workspace-mcp/agents-md)

Your own site

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

Per session 931 This file is loaded in full into every session.

When invoked 931 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	$0.00931	$0.00931
Opus 5.5	$0.00372	$0.00372
Sonnet 5.5	$0.00186	$0.00186
Haiku 4.5	$0.00093	$0.00093

Measured 2mo ago against content hash 14a2f734d5ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

shared-workspace-mcp 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 · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions

Source of truth for how agents work in this repo. Two parts: an operating contract (portable — copy to any project) and this repo (specifics). Keep everything ponytail-small.

Operating contract (portable)

Decide vs. ask

Default to deciding. Only stop and ask for the rows on the right. If a question has an obvious default, take it and say so in one line — don't block on it.

Decide yourself (no question)	Ask first
Naming, layout, formatting that match existing patterns	Adding a new dependency
Which stdlib / already-installed dep to use (ponytail ladder)	Breaking a tool contract or storage schema
Writing the smallest test / self-check for new logic	Deleting data or files; anything irreversible
Reading, searching, running checks and gates	Security-relevant change (auth, network exposure, secrets)
Commit to a branch, open a PR, update required docs	Acceptance criteria genuinely ambiguous and undefaultable

Autonomy levels

How much the agent does unattended. The gates enforce it; this just names the setting. Default: L2.

Level	The agent may, unattended	Stops for sign-off at
L0 suggest	Read, search, propose — change nothing	any write
L1 branch	Edit, run checks/gates, commit to a branch, open a PR	merge / push to main
L2 ship	L1 + merge/push to `main` once all hard gates pass	the "ask first" rows below
L3 unattended	L2 + act on schedules (dependency triage, nightly drift) without a prompt	same

No level ever skips the "Ask first" column (new dep, schema/contract break, delete, deploy, security/network). Those always need a human.

Workflow: gated by default

Run real work through the pipeline gates instead of self-declaring done:

intake — learning_search the task first, so past mistakes aren't repeated.
plan — pre-register acceptance_criteria (the definition of done).
implement — the smallest diff that works.
test — run_check; evidence must postdate your last edit (freshness).
review — verify_file_refs for any file:line claim you make.
handover — context_snapshot / handover_prepare: outcome, next steps, risks.

Read the full file on GitHub · 74 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 First seen · 74 lines · 931 tokens per session scan A 14a2f734d5ce

Subscribe to this mod's changes

shared-workspace-mcp AGENTS.md is an instructions file published in the GitHub repository WhileTrueBlackObelizk/shared-workspace-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 931 tokens to every session, about $0.0037 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 2026-08-31.

Building agents

shared-workspace-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
shared-workspace-mcp AGENTS.mdWhileTrueBlackObelizk/shared-workspace-mcp	Instructions file	0	2mo ago	MIT	A	931	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	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	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

shared-workspace-mcp: Instructions file for Codex