harness-registry

harness-registry is a skill for Claude Code from SeongwoongCho/adaptive-harness. It costs 37 tokens per session (1,340 once invoked), scanned A, original, MIT.

A registry-management skill for an adaptive coding-agent harness pool. It tracks which harnesses are stable or experimental and records their performance statistics.

In plain words
What is it for?
List harnesses, inspect their status and results, and promote or demote harnesses between pools.
Why use it?
It gives maintainers a single place to inspect and adjust the pool of specialised agents.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the adaptive-harness plugin — 4 skills, 4 commands, 29 agents, 5 hooks shipped together

Good fit List harnesses, inspect their status and results, and promote or demote harnesses between pools.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/seongwoongcho/adaptive-harness/harness-registry
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 SeongwoongCho/adaptive-harness --skill harness-registry
Clone the repo
git clone --depth 1 https://github.com/SeongwoongCho/adaptive-harness

Made for: Claude Code.

Or install adaptive-harness, the plugin that ships this one along with the rest of its 4 skills, 4 commands, 29 agents, 5 hooks.

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-registry

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/seongwoongcho/adaptive-harness/harness-registry"><img src="https://agentmods.dev/badge/skills/seongwoongcho/adaptive-harness/harness-registry.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,340 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 $0.00037 $0.01340
Opus 5 $0.00018 $0.00670
Sonnet 5 $0.00007 $0.00268
Haiku 4.5 $0.00004 $0.00134

Measured 11d ago against content hash 63b3cf330646, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

harness-registry 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 11d 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.

skills/harness-registry/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Harness Registry

Purpose

You manage the adaptive-harness harness pool. Use this skill when the user asks about harness status, wants to inspect a specific harness, or wants to promote/demote harnesses between stable and experimental pools.

Plugin Root

First, read the plugin root path: Read(".adaptive-harness/.plugin-root"). Store this as {plugin_root}. All plugin-internal file paths below use this prefix. Project state paths (.adaptive-harness/) are relative to the user's project directory.


Operations

List All Harnesses

Read .adaptive-harness/harness-pool.json and display all harnesses with their pool status and performance stats:

Read(".adaptive-harness/harness-pool.json")

Display format:

STABLE POOL
  tdd-driven          weight=1.02  successes=14  failures=2   runs=16
  systematic-debugging weight=0.98  successes=9   failures=3   runs=12
  rapid-prototype     weight=1.05  successes=21  failures=1   runs=22
  careful-refactor    weight=0.95  successes=7   failures=4   runs=11
  research-iteration  weight=1.00  successes=5   failures=0   runs=5
  code-review         weight=1.01  successes=18  failures=1   runs=19
  migration-safe      weight=0.99  successes=6   failures=1   runs=7

EXPERIMENTAL POOL
  (none)

If .adaptive-harness/harness-pool.json does not exist, report that the state directory is missing or broken. It will be auto-initialized with --general defaults on next session start. The user can trigger initialization immediately by running /adaptive-harness:run <task>.

Inspect a Specific Harness

When user asks "inspect {harness-name}" or "show me the {harness-name} harness":

Read and display:

  • {plugin_root}/agents/{name}.md — agent persona (registered in Claude Code agent registry)
  • {plugin_root}/harnesses/{name}/skill.md — workflow
  • {plugin_root}/harnesses/{name}/contract.yaml — execution contract
  • {plugin_root}/harnesses/{name}/metadata.json — current pool status and stats

Present in a structured format showing trigger conditions, tool policy, stopping criteria, cost budget, and failure modes.

Read the full file on GitHub · 136 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. 11d ago First seen · 136 lines · 37 tokens per session scan A 63b3cf330646

Subscribe to this mod's changes

harness-registry is a skill published in the GitHub repository SeongwoongCho/adaptive-harness (8 stars, last pushed 5mo ago), licensed MIT. It adds 37 tokens to every session and 1,340 once invoked, about $0.0002 per session on Opus 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.

Related

Other skills, from other repositories

relocate-claude-vm

Move the Claude Desktop "Computer Use" sandbox VM bundle (typically 11-13 GB at %APPDATA%\Claude\vmbundles on Windows) off the system drive to a roomier disk via a directory junction. Transparent to Claude Desktop, reversible. Use when the system drive is low on space and a disk scan shows vmbundles as a top consumer.…

ibrews/claude-fleet · 98 tokens

autoresearch

Autonomous experiment loop: modifies code, runs experiments, evaluates metrics, keeps improvements. Inspired by karpathy/autoresearch + pi-autoresearch + autoexp. Triggers: /autoresearch, 'auto research', 'optimize continuously', 'experiment loop', 'autonomous optimization'.

alfredolopez80/multi-agent-ralph-loop · 61 tokens

security

Claude-driven security audit with an independent second opinion. Integrates the ralph-security agent (6 quality pillars, OWASP A01-A10). Uses LSP for code navigation during analysis. Use when: (1) /security is invoked, (2) task relates to security functionality.

alfredolopez80/multi-agent-ralph-loop · 60 tokens

task-batch

Autonomous batch task execution with PRD parsing, task decomposition, and continuous execution until all tasks complete. Uses /orchestrator internally. Stops only for major failures (no internet, token limit, system crash). Use when: (1) processing task lists autonomously, (2) PRD-driven development, (3) batch feature…

alfredolopez80/multi-agent-ralph-loop · 96 tokens

diagram-design

Create technical and product diagrams — architecture, flowchart, sequence, state machine, ER / data model, timeline, swimlane, quadrant, nested, tree, layer stack, venn, pyramid — as standalone HTML files with inline SVG. Ships with a neutral editorial skin and a first-run gate that prompts users to customize the…

alfredolopez80/multi-agent-ralph-loop · 92 tokens

create-task-batch

Interactive wizard to create PRD or task lists for /task-batch. Uses /clarify and /ask-questions-if-underspecified for precise task definition. Use when: (1) preparing batch execution, (2) creating PRDs, (3) defining task lists with dependencies. Triggers: /create-task-batch, 'create tasks', 'new batch', 'prepare PRD'.

alfredolopez80/multi-agent-ralph-loop · 86 tokens