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.
npx skills add tae2089/harness --skill gemini-harnessgit clone --depth 1 https://github.com/tae2089/harnessWrote 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.
[](https://agentmods.dev/skills/tae2089/harness/gemini-harness)<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.
<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>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 | $0.00140 | $0.08324 |
| Opus 5 | $0.00070 | $0.04162 |
| Sonnet 5 | $0.00028 | $0.01665 |
| Haiku 4.5 | $0.00014 | $0.00832 |
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**: 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:
- 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. - 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_agentis 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.
- 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. - Generate the 3 elements:
.gemini/agents/+.gemini/skills/+GEMINI.md. Do not create slash commands (.gemini/commands/). - A harness is not a fixed artifact but an evolving system. Reflect feedback after each execution and continuously update agents, skills, and GEMINI.md.
- Plan Mode Required (Critical): Before starting any harness design, creation, or extension work,
enter_plan_modemust 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. - 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.
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.
- references/agent-design-patterns.md 33 KB
- references/evolution-protocol.md 5.1 KB
- references/examples/full-bundle/sso-style.md 7.0 KB
- references/examples/step/01-blog-post.md 1.5 KB
- references/examples/step/02-issue-triage.md 2.2 KB
- references/examples/step/03-architecture-design.md 2.2 KB
- references/examples/step/04-single-stage-multi-task.md 3.1 KB
- references/examples/step/05-multi-stage-multi-task.md 4.4 KB
- references/examples/step/test-scenarios.md 6.1 KB
- references/examples/team/01-fan-out-fan-in.md 4.4 KB
- references/examples/team/02-producer-reviewer.md 5.1 KB
- references/examples/team/03-supervisor.md 4.0 KB
- references/examples/team/04-hierarchical.md 5.9 KB
- references/examples/team/05-handoff-persistence.md 6.1 KB
- references/expansion-matrix.md 13 KB
- references/orchestrator-procedures.md 7.5 KB
- references/orchestrator-template.md 24 KB
- references/qa-agent-guide.md 17 KB
- references/schemas/agent-orchestrator.template.md 4.7 KB
- references/schemas/agent-state-manager.template.md 3.9 KB
- references/schemas/agent-worker.template.md 2.4 KB
- references/schemas/checkpoint.schema.json 4.2 KB
- references/schemas/findings.template.md 1.8 KB
- references/schemas/models.md 1.5 KB
- references/schemas/README.md 3.2 KB
- references/schemas/task.schema.json 2.4 KB
- references/schemas/tasks.template.md 840 B
- references/schemas/workflow.template.md 2.5 KB
- references/skill-testing-guide.md 19 KB
- references/skill-writing-guide.md 21 KB
- references/stage-step-guide.md 13 KB
- references/team-examples.md 6.5 KB
- references/usage-examples.md 11 KB
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.
- 8d ago First seen · 461 lines · 140 tokens per session scan B a783e3faf4f8
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.
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…
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…
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…
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…
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.
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…