Repository snapshot does not include a lockfile.
Agent Harness
agent-harness-maintainers/harness · v0.13.0 · Development & Workflow
Coding-agent plugin that routes project work through goals, tasks, runs, evidence gates, and state sync via project adapters
Is Agent Harness a fit?
From the plugin's manifest and HOL's scan. Anything the plugin does not declare is shown as not declared.
Works with
- Codex
- 4 skills
Before you install
- Sign-in
- Not declared
- Declared access
- Not declared
- License
- MIT
Check before relying on it
- Security checks that did not finish: cisco-skill-scanner, codex-plugin-scanner. See the evidence
What is Agent Harness?
Agent Harness is a published development & workflow plugin for AI coding agents in the codex ecosystem, developed by Agent Harness Maintainers and distributed through the HOL AI plugin registry. Coding-agent plugin that routes project work through goals, tasks, runs, evidence gates, and state sync via project adapters
- Canonical slug
- agent-harness-maintainers/harness
- Version
- v0.13.0 · updated Oct 15, 2026
- Open data
- entity.json (JSON-LD)
Trust & Reputation
Factor Analysis
Per-metric points (0–100 each) combined via a weighted average into the overall score.
Registry Snapshot
- Project link
- Agent Harness
- Canonical profile
- https://hol.org/registry/plugins/agent-harness-maintainers%2Fharness
- Publisher verification
- No
- Marketplace source
- Unknown
- Scanner
- Broker fallback
- Security result
- Partial scan
- Digest verified
- Yes
Trust & reputation
Trust & Reputation
Factor Analysis
Per-metric points (0–100 each) combined via a weighted average into the overall score.
Provenance
- Plugin root
- plugins/agent-harness
- Source repo
- https://github.com/0xenzyme/agent-harness
- Source commit
- 766cafa2f315…
- Publisher verified
- No
- Owner verified
- @0xenzyme
Continuous scanner CI not detected
This plugin remains listed. Its overall trust score is reduced by 10% because security checks are not maintained in the source repository's CI.
Optional: maintain the scanner in the source repository's CI to receive the full trust score. Listing does not require that change.
README badge not detected
Plugin owners can add the HOL badge to the repository README from Guard Plugins. Distribution, not security evidence. It adds a 2% engagement adjustment to the overall trust score and never changes the security result.
Security Posture
See how the Trust Score is computedSome checks did not finish (cisco-skill-scanner, codex-plugin-scanner). No blocking issue was found in the checks that did finish, but this is not a passed scan.
- Provider
- registry-broker-fallback
- Grade
- A · safe
- Version
- Unknown
Findings
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner exited with code 1: Error loading skill: No SKILL.md and no .md files found in /tmp/hol-skill-safety-glBNbE (lenient mode requires at least one markdown file)
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner timed out after 60000 ms
Agent Harness — Frequently asked questions
- What is Agent Harness?
- Agent Harness is an AI plugin in the HOL registry. Coding-agent plugin that routes project work through goals, tasks, runs, evidence gates, and state sync via project adapters
- How do I install Agent Harness?
- Install Agent Harness in your harness: Codex — codex plugin marketplace add 0xenzyme/agent-harness; Any agent — npx [email protected] add 0xenzyme/agent-harness. Full step-by-step guidance is on the HOL plugin page.
- How do I install Agent Harness in Codex?
- To install Agent Harness in Codex, start with codex plugin marketplace add 0xenzyme/agent-harness. The complete step-by-step install guide for Codex is on the HOL plugin page.
- Is Agent Harness free?
- Pricing for Agent Harness is published on its HOL plugin page when the maker schedules a launch.
- How is the Trust Score for Agent Harness computed?
- Agent Harness has a HOL Trust Score of 78 out of 100. The score is a weighted sum of six components from a static scan of the source, capped for high-severity findings and adjusted by two disclosed policies. Memberships and payments are not inputs, and a scan is not a safety guarantee. Full breakdown: https://hol.org/registry/plugins/agent-harness-maintainers%2Fharness/trust
- Who publishes Agent Harness?
- Agent Harness is published by Agent Harness Maintainers and listed on HOL.
- Is Agent Harness available now?
- Agent Harness availability is listed on its HOL plugin page.
Install Guidance
Install in Codex
Install through the Codex CLI plugin marketplace.
Optional: install HOL Guard for Codex first, so it can check this plugin's tools on your machine before Codex uses them.
- 1
Register the marketplace
Run in any terminal. Codex reads the marketplace entry from .agents/plugins/marketplace.json (or the legacy .claude-plugin path) in the repository. If the repository ships none, add the generated entry from the Advanced section below first.
shell - 2
Install from the Plugins browser
Open Codex, open the Plugins browser, choose the marketplace registered by the previous command, and install harness.
- 3
Check the marketplace is registered
This confirms the marketplace source only. Confirm the plugin itself is enabled in the Plugins browser before relying on it.
shell
Did setup work in Codex?
No setup reports for Codex yet. Self-reported by signed-in visitors. Copying a command is not counted, and most installs are never reported.
Attested installs: Fewer than 10 attested installs of this plugin in week 2026-W43, so no number is shown. Counted from opt-in HOL Guard install reports, once per machine and runtime, and never mixed with the answers above. How install reports work.
Loading reviews
Plugin Manifest
{
"name": "harness",
"version": "0.13.0",
"description": "Reusable coding-agent harness for workflow-oriented project task control and adapter-driven execution. / 可复用项目任务控制与 adapter 执行工作流。",
"author": {
"name": "Agent Harness Maintainers"
},
"homepage": "https://github.com/0xenzyme/agent-harness",
"repository": "https://github.com/0xenzyme/agent-harness",
"license": "MIT",
"keywords": [
"coding-agent",
"harness",
"tasks",
"goals",
"workflow"
],
"skills": "./",
"interface": {
"displayName": "Agent Harness",
"developerName": "Agent Harness Maintainers",
"shortDescription": "Orient, intake, initialize, and execute adapter-driven project work. / 定位、收集、初始化并执行 adapter 驱动的项目工作。",
"longDescription": "Agent Harness bridges host runtime outcome, transient plan, session, and worker execution with durable fixed/adapter project control: authoritative Task/Goal state, repository Runs/DAGs, postflight state sync, gates, and evidence. zh-CN fallback: Agent Harness 把 host 的 runtime outcome、transient plan、会话和 worker 执行连接到持久化 fixed / adapter 项目控制,包括权威 Task/Goal 状态、repository Run/DAG、postflight 状态同步、gate 和 evidence。",
"category": "Productivity",
"capabilities": [
"Project task control",
"Host runtime outcome and plan bridge",
"Postflight state sync",
"Goal handoff",
"Run preparation",
"Loop engineering"
],
"websiteURL": "https://github.com/0xenzyme/agent-harness",
"privacyPolicyURL": "https://github.com/0xenzyme/agent-harness/blob/main/plugins/agent-harness/PRIVACY.md",
"termsOfServiceURL": "https://github.com/0xenzyme/agent-harness/blob/main/LICENSE",
"composerIcon": "./assets/icon.svg",
"logo": "./assets/logo.svg",
"screenshots": [
"./assets/screenshot.png"
],
"defaultPrompt": [
"Use harness:orient to inspect durable state and choose host-direct, host-direct-postflight, or durable-harness. Prefer native runtime outcome and transient plan when the host exposes them."
]
},
"holManifestOrigin": "repository",
"registryIndexVersion": 5
}Marketplace Source
- Repo URL
- https://github.com/0xenzyme/agent-harness
- Marketplace path
- Unknown
- Source path
- plugins/agent-harness
- Install policy
- Unspecified
Skills
4 SKILL.md files ship with this plugin. Preview, copy, or download each one, then install them with the Skills CLI.
skills/execute/SKILL.md
Execute accepted long-running controller or durable Harness work, or postflight-sync already tracked work; ordinary clear changes use the current host directly. / 执行主控长任务、持久化控制或已有状态同步。
SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.
skills/init/SKILL.md
Explicitly audit, initialize, import, or repair Agent Harness setup and config migration; not for ordinary status, intake, or product implementation. / 显式接入、迁移或修复 Harness。
SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.
skills/intake/SKILL.md
Explicitly preview or record rough Agent Harness ideas, requirements, bugs, and inbox notes without accepting scope or implementing it. / 显式收集未确认事项,不执行。
SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.
skills/orient/SKILL.md
Inspect durable Agent Harness state and recommend the next public entry without mutation. Use for status, blockers, stale artifacts, or route questions. / 只读检查持久化状态与下一入口。
SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.
File Inventory
.codex-plugin/plugin.json
plugin-manifest
2,018 bytes
e889631a2991fd95…
assets/icon.svg
asset
748 bytes
795fdaebc5e590ed…
assets/logo.svg
asset
1,167 bytes
f63cd8e8d83495f2…
assets/screenshot.png
asset
182,816 bytes
75584a9ca477eb70…
README.md
file
1,937 bytes
57591adc9f67a181…
SECURITY.md
file
617 bytes
2120c3ea582103e4…
skills/execute/agents/openai.yaml
skill
414 bytes
cd89f28b53052373…
skills/execute/references/completion-evidence.md
skill
1,438 bytes
c5763ebcf3019eaf…
skills/execute/SKILL.md
skill
13,672 bytes
492abc5f8b19de34…
skills/init/agents/openai.yaml
skill
242 bytes
47db1add784b72ab…
skills/init/references/setup-migration-safety.md
skill
557 bytes
048d86d7a50e0f76…
skills/init/SKILL.md
skill
2,004 bytes
69465bb2c722578e…
skills/intake/agents/openai.yaml
skill
241 bytes
ba8623cedcd49596…
skills/intake/references/capture-promotion.md
skill
630 bytes
bce88f263142b183…
skills/intake/SKILL.md
skill
1,765 bytes
b2563b115022eaf4…
skills/orient/agents/openai.yaml
skill
266 bytes
2da2f48289550b02…
skills/orient/SKILL.md
skill
3,480 bytes
35df226268c4f0fe…
Related plugins
Ordered by Trust Score. Listings cannot pay for these positions. Check each one fits your task before switching from Agent Harness.
Alternatives in Development & Workflow
- Agent DeckOne MCP for context management: bind self-improving playbooks, MCP tools, and API keys to the session.Trust 92 · Scan: safe · MCP, Codex, Claude Code
- ArmorCodexIntent-based security for Codex with MCP plan registration, policy gating, CSRG cryptographic proofs, and audit logging on `bash` and `apply_patch`.Trust 92 · Scan: safe · MCP, Codex
- AtomLaneParallelizes only work proven safe by compiling resource-aware atomic plans for builds, tests, Make/Compose workflows, and long-running jobs with live progress and measured savings.Trust 92 · Scan: safe · Codex
- Codex Process JobsRun long local builds, tests, benchmarks, and inference jobs as durable detached processes with tracked status, bounded results, and completion delivery across Codex surfaces.Trust 92 · Scan: safe · Codex
History, reviews, and alternatives
Launch history
No public launch record yet.
User reviews
The first substantive review can be added on this page.
Milestones and alternatives
Related alternatives
Suggested from HOL scan evidence: same category, at least one shared runtime, similar tags and contents. Paid placement and Trust Score play no part.
