agent: Instructions file for Gemini CLI

GEMINI.md

agent GEMINI.md is an instructions file for Gemini CLI from adaptlypost/agent. It costs 496 tokens per session, scanned A, original, MIT.

A set of instructions that connects Gemini CLI, a command-line coding assistant, to an AdaptlyPost workspace for managing social media.

In plain words
What is it for?
It helps list connected accounts, draft and schedule posts across social networks, and compare engagement over time.
Why use it?
It explains sign-in and safe use so you can avoid guessing settings or accidentally changing or deleting workspace content.

Instructions file for Gemini CLI

Written for Gemini CLI: the file is GEMINI.md. Also seen: mentions Gemini CLI.

This is adaptlypost/agent's own configuration. It tells Gemini CLI how to work on agent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to adaptlypost/agent. 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/adaptlypost/agent/main/GEMINI.md
Clone the repo
git clone --depth 1 https://github.com/adaptlypost/agent

Made for: Gemini CLI.

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.

agentmods badge for agent GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/adaptlypost/agent/gemini-md/github.svg)](https://agentmods.dev/instructions/adaptlypost/agent/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/adaptlypost/agent/gemini-md"><img src="https://agentmods.dev/badge/instructions/adaptlypost/agent/gemini-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.

agentmods 80×15 button for agent GEMINI.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/adaptlypost/agent/gemini-md"><img src="https://agentmods.dev/badge/instructions/adaptlypost/agent/gemini-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 496 This file is loaded in full into every session.
When invoked 496 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00496 $0.00496
Opus 5.5 $0.00198 $0.00198
Sonnet 5.5 $0.00099 $0.00099
Haiku 4.5 $0.00050 $0.00050

Measured 9d ago against content hash ef0444300347, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent GEMINI.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 9d 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.

GEMINI.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AdaptlyPost

AdaptlyPost schedules and publishes social posts across Instagram, TikTok, YouTube, X, LinkedIn, Facebook, Pinterest, Threads, Bluesky, Mastodon, Google Business Profile, Tumblr, Telegram and WordPress. This extension connects Gemini CLI to an AdaptlyPost workspace over MCP.

Signing in

The server is at https://mcp.adaptlypost.com/mcp. It answers an unauthenticated call with a 401 and points at its OAuth metadata, so Gemini CLI opens a browser the first time a tool runs. Sign in with the AdaptlyPost account that owns the workspace. Nothing needs to be configured by hand, and no API token is stored in this extension.

What to ask for

  • "list the accounts I have connected"
  • "draft a post for LinkedIn and X about our new release, schedule it for tomorrow 09:00"
  • "how did last month compare to the one before on engagement?"
  • "show the unread comments and messages in my inbox"

Notes

  • A sign-in can reach several workspaces. list_workspaces lists them, and every other tool takes an optional workspaceId. In each workspace a tool acts with the account's own role there: Admin, Editor, Contributor or Viewer. A Contributor can draft and upload media but cannot schedule or publish; a Viewer only reads.
  • A 403 with code: permission_denied is final. Do not retry it and do not look for another key. For scheduling or publishing, save the post as a draft (saveAsDraft: true, keeping scheduledAt as its planned date) and tell the user a workspace member has to publish it. publish_draft without a date schedules such a draft for its planned date when that is still in the future.
  • Ask before anything that writes. Deletes cannot be undone.
  • Inbox replies, direct messages and review replies reach real people. Show the exact text and the item it answers, and wait for a yes before sending. A 403 with code: inbox_reconnect_required means the account must be reconnected in AdaptlyPost; do not retry it.
  • Read the tool descriptions for the filters each one accepts rather than guessing parameter names.

Read the full file on GitHub · 40 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.

  1. 9d ago Changed · +5 lines · +84 tokens per session ef0444300347
  2. 20d ago Changed · +2 lines · +38 tokens per session 905c8e29f141
  3. 1mo ago Changed · +6 tokens per session 5de02fed3100
  4. 1mo ago Changed · +1 lines · +23 tokens per session 92fcaf543974
  5. 1mo ago Changed · +5 lines · +102 tokens per session 6f0171cc1cda
  6. 2mo ago First seen · 27 lines · 243 tokens per session scan A 45f36fecf8fa

Subscribe to this mod's changes

agent GEMINI.md is an instructions file published in the GitHub repository adaptlypost/agent (0 stars, last pushed yesterday), licensed MIT. It adds 496 tokens to every session, about $0.0020 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 2026-09-18.

Related

agent GEMINI.md compared with instructions from other repositories

agent GEMINI.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
agent GEMINI.mdadaptlypost/agentInstructions file0yesterdayMITA496Gemini CLI
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150kyesterdayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file283kyesterdayMITA4,342Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot