gemini-harness

gemini-harness is a skill for Claude Code, Codex from tae2089/harness. It costs 140 tokens per session (8,324 once invoked), scanned B, original, Apache-2.0.

A planning framework for the Gemini command-line environment that designs teams of specialized helper agents and the skills they use to work together.

In plain words
What is it for?
Use it to build or reconfigure a Gemini agent harness, define agent roles and tools, and create shared procedures and an orchestrator.
Why use it?
It helps organize agent roles, permissions, collaboration patterns, and project automation when a task is too broad for one agent.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for aider. Also seen: mentions subagents; mentions Claude Code; mentions AGENTS.md.

Good fit Use it to build or reconfigure a Gemini agent harness, define agent roles and tools, and create shared procedures and an orchestrator.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tae2089/harness/gemini-harness
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.

Any agent
npx skills add tae2089/harness --skill gemini-harness
Clone the repo
git clone --depth 1 https://github.com/tae2089/harness

Made for: Claude Code, Codex.

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-harness

README.md
[![agentmods](https://agentmods.dev/badge/skills/tae2089/harness/gemini-harness/github.svg)](https://agentmods.dev/skills/tae2089/harness/gemini-harness)
Your own site
<a href="https://agentmods.dev/skills/tae2089/harness/gemini-harness"><img src="https://agentmods.dev/badge/skills/tae2089/harness/gemini-harness/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 gemini-harness

Your own site · 80×15
<a href="https://agentmods.dev/skills/tae2089/harness/gemini-harness"><img src="https://agentmods.dev/badge/skills/tae2089/harness/gemini-harness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 140 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,324 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00140 $0.08324
Opus 5 $0.00070 $0.04162
Sonnet 5 $0.00028 $0.01665
Haiku 4.5 $0.00014 $0.00832

Measured 8d ago against content hash a783e3faf4f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

gemini-harness scanned grade B with 1 finding 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 8d 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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

2. **Strict Tool Permission Control:** Assign only tools optimized for each agent's role; `tools: ["*"]` is prohibited. However, **all agents must include the following tools**:
skills/gemini-harness/SKILL.md · 461 lines

How it starts

The opening of the file, as written. The whole thing — 461 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Harness — Subagent Orchestration & Skill Architect

A meta-skill that configures a harness suited to the domain/project, defines each subagent's role and tool permissions, and creates procedure skills and an orchestrator for agents to use in common.

Core Principles:

  1. Apply 7 Core Architecture Patterns: Select the optimal collaboration structure for the problem characteristics (Pipeline, Fan-out/Fan-in, Expert Pool, Producer-Reviewer, Supervisor, Hierarchical, Handoff). Details: references/agent-design-patterns.md.
  2. Strict Tool Permission Control: Assign only tools optimized for each agent's role; tools: ["*"] is prohibited. However, all agents must include the following tools:
    • ask_user: Used to ask the user for clarification instead of guessing when instructions are ambiguous or data conflicts arise.
    • activate_skill: Essential for agents to load and execute procedure skills (methodologies, checklists, protocols) under .gemini/skills/ at runtime.
    • invoke_agent is only permitted for orchestrators, Supervisors, and Hierarchical team leads (Mid-level) — prohibited for regular worker agents. Both sequential (wait_for_previous: true) and parallel (wait_for_previous: false) use is supported.
  3. Main Agent Orchestration and Persistence: Since Gemini CLI has no direct inter-subagent communication (SendMessage) API, the main agent acts as the sole data broker (_workspace/findings.md), state manager (_workspace/checkpoint.json), and task board (_workspace/tasks.md) manager.
  4. Generate the 3 elements: .gemini/agents/ + .gemini/skills/ + GEMINI.md. Do not create slash commands (.gemini/commands/).
  5. A harness is not a fixed artifact but an evolving system. Reflect feedback after each execution and continuously update agents, skills, and GEMINI.md.
  6. Plan Mode Required (Critical): Before starting any harness design, creation, or extension work, enter_plan_mode must be called. Isolate the research and design phases to ensure stability of complex orchestration logic, and only implement in code the plan that has received final user approval. However, in yolo mode, proceed directly.
  7. Zero-Tolerance Failure Protocol: Arbitrarily skipping test failures or rejected agent outputs is strictly prohibited. The main agent and supervisors must always seek a solution (maximum 2 retries, 3 total); if unresolved, do not autonomously proceed to the next step — immediately halt and request user intervention.

Read the full file on GitHub · 461 lines

Files

What ships with it

33 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 461 lines · 140 tokens per session scan B a783e3faf4f8

Subscribe to this mod's changes

gemini-harness is a skill published in the GitHub repository tae2089/harness (4 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 140 tokens to every session and 8,324 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

temporal

Resolve ANY named time window — today, yesterday, thisWeek, lastWeek, last7Days, last30Days, last90Days, thisMonth, lastMonth, thisQuarter, lastQuarter, thisYear, lastYear, last12Months — or an arbitrary range (lastNdays / lastNweeks / lastNmonths) to a concrete ISO date range relative to your run time. Read-only: no…

chaitanyagiri/munder-difflin · 114 tokens

last30Days

Resolve "last30Days" to a concrete ISO date range relative to your run time — a rolling 30-day window ending today. Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a "last 30 days" / trailing-month task…

chaitanyagiri/munder-difflin · 83 tokens

thisQuarter

Resolve "thisQuarter" to a concrete ISO date range relative to your run time — this quarter so far (quarter start → today). Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a quarter-to-date task (QTD…

chaitanyagiri/munder-difflin · 78 tokens

thisWeek

Resolve "thisWeek" to a concrete ISO date range relative to your run time — this week so far (Monday → today). Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a week-to-date task (this week's activity…

chaitanyagiri/munder-difflin · 77 tokens

harness

A meta-skill for designing and maintaining a project harness: a coordinated set of specialist agents, skills, and project instructions. It defines their roles, connects them to the project, and updates the setup as the work changes.

revfactory/harness · 170 tokens

md-hive-sync

Munder Difflin hive sync — runs the start-of-task hive protocol steps: reads memory.md, checks inbox/ for new messages, and reminds you to record durable facts in memory.md and write coordination files before ending. Use when asked to "sync with the hive", "check my inbox", "hive status", or "hive sync". Proactively…

chaitanyagiri/munder-difflin · 109 tokens