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 SeongwoongCho/adaptive-harness --skill harness-registrygit clone --depth 1 https://github.com/SeongwoongCho/adaptive-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/seongwoongcho/adaptive-harness/harness-registry)<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.
<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>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 | $0.00037 | $0.01340 |
| Opus 5 | $0.00018 | $0.00670 |
| Sonnet 5 | $0.00007 | $0.00268 |
| Haiku 4.5 | $0.00004 | $0.00134 |
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.
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.
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.
- 11d ago First seen · 136 lines · 37 tokens per session scan A 63b3cf330646
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.
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.…
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'.
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.
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…
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…
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'.