second-thought-agent-skill GEMINI.md

second-thought-agent-skill GEMINI.md is an instructions file for Gemini CLI from gg-mo/second-thought-agent-skill. It costs 29 tokens per session, scanned A, original, MIT.

A set of instructions for an AI coding agent to question plans and decisions before carrying them out.

In plain words
What is it for?
It is for reviewing proposed approaches, identifying risks, and improving decisions during coding work.
Why use it?
It helps catch flaws, risks, and weak assumptions early, before they become costly changes.

Instructions file for Gemini CLI

Install

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.

agentmods
npx agentmods add instructions/gg-mo/second-thought-agent-skill/gemini-md
Clone the repo
git clone --depth 1 https://github.com/gg-mo/second-thought-agent-skill

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 second-thought-agent-skill GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/gg-mo/second-thought-agent-skill/gemini-md.svg)](https://agentmods.dev/instructions/gg-mo/second-thought-agent-skill/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/gg-mo/second-thought-agent-skill/gemini-md"><img src="https://agentmods.dev/badge/instructions/gg-mo/second-thought-agent-skill/gemini-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 This file is loaded in full into every session.
When invoked 29 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00029 $0.00029
Opus 5 $0.00015 $0.00015
Sonnet 5 $0.00006 $0.00006
Haiku 4.5 $0.00003 $0.00003

Measured 4d ago against content hash ae0e7a24116b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

second-thought-agent-skill 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 4d 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 · 3 lines

What it actually says

@./skills/using-second-thought/SKILL.md @./skills/using-second-thought/references/gemini-tools.md

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. 4d ago First seen · 3 lines · 29 tokens per session scan A ae0e7a24116b

Subscribe to this mod's changes

second-thought-agent-skill GEMINI.md is an instructions file published in the GitHub repository gg-mo/second-thought-agent-skill (5 stars, last pushed 4mo ago), licensed MIT. It adds 29 tokens to every session, about $0.0001 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 2026-08-31.

Related

Other instructions, from other repositories

claude-skill-b2-cloud-storage CLAUDE.md

Instructions for backblaze-labs/claude-skill-b2-cloud-storage, covering claude.md, layout, ci conventions, workflow-security invariants and commits.

backblaze-labs/claude-skill-b2-cloud-storage · 656 tokens

Lycheetah-Framework AGENTS.md

Instructions for Lycheetah/Lycheetah-Framework, covering codex transition overlay — caelorynth, sol protocol v3.0 — operating architecture, sovereign human–ai co-creation system, i. what this is and ii. identity.

Lycheetah/Lycheetah-Framework · 3,621 tokens

agent-capability-standard CLAUDE.md

Instructions for synaptiai/agent-capability-standard, covering claude.md, commands, validate workflows against the ontology, validate domain profiles against schema and validate skill file references (no phantom paths).

synaptiai/agent-capability-standard · 2,946 tokens

Lycheetah-Framework copilot-instructions.md

Instructions for Lycheetah/Lycheetah-Framework, covering copilot instructions for lycheetah-framework, quick reference, for copilot users and mathematics standard.

Lycheetah/Lycheetah-Framework · 358 tokens

slushpile GEMINI.md

Instructions for VonTerraProject501c3/slushpile, covering slushpile, setup, once per workspace, the skills, the agents and what this never does.

VonTerraProject501c3/slushpile · 613 tokens

Lycheetah-Framework CLAUDE.md

Instructions for Lycheetah/Lycheetah-Framework, covering sol — claude execution anchor, authority and purpose, canonical source map, sol's functional identity and relationship with mac.

Lycheetah/Lycheetah-Framework · 4,913 tokens