GEMINI

GEMINI is an agent for coding agents from ApexIQ/skillsmith. It costs 0 tokens per session (889 once invoked), scanned A, original, MIT.

The following 33+ commands are available as structured workflows: brainstorm, plan-feature, implement-feature, review-changes, test-changes, deploy-checklist, debug-issue, refactor, debug, test, doc, audit, lint, compose, evolve, align, profile, report, sync, autonomous, context, verify, review, bootstrap, migrate…

Agent

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 agents/apexiq/skillsmith/gemini
Clone the repo
git clone --depth 1 https://github.com/ApexIQ/skillsmith

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 GEMINI

README.md
[![agentmods](https://agentmods.dev/badge/agents/apexiq/skillsmith/gemini.svg)](https://agentmods.dev/agents/apexiq/skillsmith/gemini)
Your own site
<a href="https://agentmods.dev/agents/apexiq/skillsmith/gemini"><img src="https://agentmods.dev/badge/agents/apexiq/skillsmith/gemini.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 889 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00000 $0.00889
Opus 5 $0.00000 $0.00445
Sonnet 5 $0.00000 $0.00178
Haiku 4.5 $0.00000 $0.00089

Measured today against content hash 1c6d65ac3c4d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

GEMINI 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 today.

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.

docs/agents/GEMINI.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.

GEMINI.md

Prime Directives

  1. Read AGENTS.md, .agent/STATE.md, and .agent/lessons.md first.
  2. Read .agent/principles/CORE_PRINCIPLES.md for project behavioral rules.
  3. Read .agent/project_profile.yaml, and .agent/context/project-context.md.
  4. Search .agent/skills/ before implementation.
  5. Follow the 7-Stage Workflow: Discover → Plan → Build → Review → Test → Ship → Reflect.

7-Stage Workflow

  1. Discover: Audit profile, context, and code for constraints.
  2. Plan: Define minimal patch with verification points.
  3. Build: Implement atomic changes in isolation.
  4. Review: Adversarial check for risks and regressions.
  5. Test: Identify highest-risk behavior and verify.
  6. Ship: Generate clean handoff with evidence.
  7. Reflect: Record lessons and update project state.

Execution Policy

  • Plan before coding for non-trivial work (3+ steps or architectural impact).
  • Keep changes minimal, explicit, and easy to verify.
  • Use subagents only when parallelism or specialization is clearly beneficial.
  • Verify with tests/checks before marking done.

Memory and Cost Policy

  • Library-First: skillsmith is the source of truth for memory.
  • Mandatory Memory Protocol:
    • Read .agent/lessons.md (Layer 2) for long-term project memory and past mistakes.
    • Log tactical events to .agent/logs/raw_events.jsonl (Layer 1).
  • Autonomous Evolution:
    • Run skillsmith evolve reflect after multi-step missions to distill logs into lessons.
  • Use the five-layer pattern: observer, reflector, recovery, watcher, safeguard.
  • Cache reuse must be guarded by TTL and context/policy fingerprints.

Role Use

  • orchestrator: own task framing, delegation decisions, and final readiness.
  • researcher: collect repository facts, constraints, and edge cases first.
  • implementer: apply minimal code changes with verification evidence.
  • reviewer: perform findings-first checks for correctness and regressions.

Role Handoff

  • Pass goal, scope, file list, risks, and verification evidence between roles.
  • Prefer researcher -> implementer -> reviewer -> orchestrator for non-trivial work.

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.

  1. today First seen · 74 lines · 0 tokens per session scan A 1c6d65ac3c4d

Subscribe to this mod's changes

GEMINI is an agent published in the GitHub repository ApexIQ/skillsmith (5 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 889 tokens. 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 2026-09-03.

Related

Other agents, from other repositories

ralph-loop-runner

Use this agent when you need to execute a Ralph orchestration loop end-to-end and verify its completion. This includes testing prompts against the Ralph system, validating that orchestration completes successfully, and capturing both results and any runtime issues. Examples:\n\n \nContext: User wants to test if a…

mikeyobrien/ralph-orchestrator · 286 tokens

otp-advisor

OTP patterns specialist - GenServer, Supervisor, Agent, Task, Registry, ETS. Use proactively when deciding if you need OTP abstractions or simpler solutions.

oliver-kriska/claude-elixir-phoenix · 35 tokens

adr-critic

Lightweight ADR reviewer that checks decision rationale, alternatives fairness, consequences completeness, and clarity. Reads Author's Notes as prioritized attack vectors. Use when the ADR review operation needs a quick quality check.

joaquimscosta/arkhe-claude-plugins · 43 tokens

due-diligence-lead

Due diligence specialist who validates assumptions, identifies risks, and stress-tests business claims. Use this skill when someone needs due diligence, risk assessment, assumption validation, says things like 'stress test my business', 'validate my assumptions', 'due diligence', 'red flags', 'risk assessment', 'is…

NOMARJ/sigil · 121 tokens

explorer

Fast codebase explorer that finds files, traces symbols, and answers structure questions at a chosen depth.

NicoGenti/opencode-orchestrator-kit · 20 tokens

unity-ui-pro

Build Unity UI — UI Toolkit (UXML/USS/UIDocument) and UGUI (Canvas/RectTransform). Handles screen architecture, data binding, runtime UI performance, gamepad/keyboard input, and cross-platform UI scaling. Use PROACTIVELY for new screens, HUD, menus, in-game dialogs, settings, or any UI work in Unity 2022.3+. Not for…

AcKeskin/contexture · 102 tokens