agentmods.dev

harness-agent-assets

harness-agent-assets is a skill for Claude Code, Codex from guyuefangyuanl/deepseek-better-harness. It costs 59 tokens per session (216 once invoked), scanned A, original, MIT.

A guide for auditing the tools, instructions, presets, hooks, commands, and other assets that control how coding agents discover and route work.

In plain words
What is it for?
Use it to inspect agent configurations and skills, verify links and schemas, check discovery and loading, and review approval or cleanup boundaries.
Why use it?
It helps distinguish assets that merely exist from those that load and work correctly, while identifying routing errors, unsafe behaviour, and ownership conflicts.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 1repo 2mo ago A scan 59 tokens original MIT

Good fit Use it to inspect agent configurations and skills, verify links and schemas, check discovery and loading, and review approval or cleanup boundaries.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/guyuefangyuanl/deepseek-better-harness/harness-agent-assets
View source ↗ guyuefangyuanl/deepseek-better-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 guyuefangyuanl/deepseek-better-harness --skill harness-agent-assets
Clone the repo
git clone --depth 1 https://github.com/guyuefangyuanl/deepseek-better-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 harness-agent-assets

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/guyuefangyuanl/deepseek-better-harness/harness-agent-assets"><img src="https://agentmods.dev/badge/skills/guyuefangyuanl/deepseek-better-harness/harness-agent-assets.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 216 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00059 $0.00216
Opus 5.5 $0.00024 $0.00086
Sonnet 5.5 $0.00012 $0.00043
Haiku 4.5 $0.00006 $0.00022

Measured 2mo ago against content hash df6d818f1f54, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

harness-agent-assets 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 2mo 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.

packages/agent-assets/skills/harness-agent-assets/SKILL.md · 21 lines

What it actually says

Harness Agent Assets

Review configured Agent assets as executable routing and control surfaces.

  1. Resolve the host, scope, asset roots, and precedence before counting assets.
  2. Inventory only supported asset types and distinguish configured, discovered, loadable, enabled, and actually exercised states.
  3. Validate names, routing descriptions, links, schemas, referenced files, duplicate ownership, and teardown or approval boundaries where applicable.
  4. Treat zero or high counts as navigation facts, not findings by themselves.
  5. Report an issue only when evidence ties the asset defect to wrong routing, unsafe behavior, failed loading, stale instructions, or user friction.

Read references/agent-assets-contract.md for scope and integrity rules.

Files

What ships with it

1 file 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. 2mo ago First seen · 21 lines · 59 tokens per session scan A df6d818f1f54

Subscribe to this mod's changes

harness-agent-assets is a skill published in the GitHub repository guyuefangyuanl/deepseek-better-harness (1 stars, last pushed 2mo ago), licensed MIT. It adds 59 tokens to every session and 216 once invoked, about $0.0002 per session on Opus 5.5. 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.

Building agentsagent-skillsai-agentbetter-harnessdeepseek-harnessdsh-pluginqoder
Related

harness-agent-assets compared with skills from other repositories

harness-agent-assets next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
harness-agent-assetsguyuefangyuanl/deepseek-better-harnessSkill12mo agoMITA59Claude Code, Codex
feynman-perspectivealchaincyf/nuwa-skillSkill38kyesterdayMITA212Claude Code, Codex
naval-perspectivealchaincyf/nuwa-skillSkill38kyesterdayMITA218Claude Code, Codex
x-mastery-mentoralchaincyf/nuwa-skillSkill38kyesterdayMITA197Claude Code, Codex
elon-musk-perspectivealchaincyf/nuwa-skillSkill38kyesterdayMITA228Claude Code, Codex
ilya-sutskever-perspectivealchaincyf/nuwa-skillSkill38kyesterdayMITA183Claude Code, Codex
dsh-tui-guideccch1mneyyy/dsh-TUISkill7.4ktodayMITA41Claude Code, Codex