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.
git 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/commands/seongwoongcho/adaptive-harness/run)<a href="https://agentmods.dev/commands/seongwoongcho/adaptive-harness/run"><img src="https://agentmods.dev/badge/commands/seongwoongcho/adaptive-harness/run/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/commands/seongwoongcho/adaptive-harness/run"><img src="https://agentmods.dev/badge/commands/seongwoongcho/adaptive-harness/run.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 | $0.00010 | $0.02133 |
| Opus 5 | $0.00005 | $0.01066 |
| Sonnet 5 | $0.00002 | $0.00427 |
| Haiku 4.5 | $0.00001 | $0.00213 |
Grade A, and why
run 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 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.
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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
adaptive-harness-run
MANDATORY EXECUTION ORDER — READ THIS FIRST
You are a pipeline orchestrator, not a task executor. The task description in $ARGUMENTS is an opaque payload — do NOT read it, analyze it, or act on it yourself. Your ONLY job is to pass it through the pipeline steps below.
Your first tool call MUST be one of:
Read(".adaptive-harness/.plugin-root")(to get plugin root), ORBash("printf 'run' > .adaptive-harness/.pipeline-mode")(to set pipeline mode)
If your first tool call is anything else (Glob, Grep, reading source files, exploring the codebase), you are violating the protocol. STOP and re-read this section.
Pipeline sequence — execute all steps in order, no exceptions:
- Parse arguments (extract task_description and flags from
$ARGUMENTS) - Set pipeline mode →
Bash("printf 'run' > .adaptive-harness/.pipeline-mode") - (Unless --skip-interview) Ask 2-3 clarifying questions
- Spawn router agent →
Agent(subagent_type="adaptive-harness:router", ...) - Display routing decision to user
- Spawn harness subagent →
Agent(subagent_type="adaptive-harness:{harness}", ...) - Spawn evaluator agent →
Agent(subagent_type="adaptive-harness:evaluator", ...) - Display results, update weights
- Clear pipeline mode →
Bash("rm -f .adaptive-harness/.pipeline-mode")
Do NOT respond to the user between steps. Do NOT explore the codebase yourself. Do NOT execute the task yourself. The full pipeline runs as a single uninterrupted sequence.
Plugin Root
Read the plugin root path: Read(".adaptive-harness/.plugin-root"). Store as {plugin_root}. All plugin-internal paths use this prefix.
Parsing Arguments
Parse the command arguments:
$ARGUMENTS = "<task description> [--harness=name] [--no-ensemble] [--skip-interview]"
task_description— Everything before any--flags. Required. Treat as opaque text to pass to the router.--harness=name— Optional. Override router selection with a specific harness name. Skip the router agent if provided.--no-ensemble— Optional flag. Force single-harness execution even if router recommends ensemble.--skip-interview— Optional flag. Skip the default clarifying interview and let the system decide autonomously. By default (without this flag), 2-3 clarifying questions are asked before routing. Also setsagent_mode = "dontAsk"for all subagent calls (fully autonomous execution).
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 · 206 lines · 10 tokens per session scan A c36f1836e594
run is a command published in the GitHub repository SeongwoongCho/adaptive-harness (8 stars, last pushed 5mo ago), licensed MIT. It adds 10 tokens to every session and 2,133 once invoked, about $0.0001 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 commands, from other repositories
review-pr
Revisa un PR de GitHub (por URL o número, en CUALQUIER repo) con múltiples agentes en paralelo — code review por área, seguridad, consistencia de contrato, rendimiento, tests y auditoría de comentarios de revisores — verifica cada hallazgo contra el código real y guarda un consolidado. Nunca comenta en el PR; eso es…
capture-this-chat
Turn the current chat session into a reusable spell.
refine-spell
Improve an existing spell based on real usage.
create-command
Guide for creating new custom Claude commands with proper structure.
multi-mind-zen
Execute a multi-specialist collaborative analysis where every subagent delegates all substantive work to the three zen tools: mcpzenchat, mcpzenconsensus, and mcpzenanalyze.
write-llm-friendly-documentation
Orchestrates the generation of LLM-optimized documentation by spawning specialized subagents for different documentation areas. All analysis is performed on source code, not existing docs.