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/status)<a href="https://agentmods.dev/commands/seongwoongcho/adaptive-harness/status"><img src="https://agentmods.dev/badge/commands/seongwoongcho/adaptive-harness/status/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/status"><img src="https://agentmods.dev/badge/commands/seongwoongcho/adaptive-harness/status.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 | $0.00013 | $0.01131 |
| Opus 5 | $0.00006 | $0.00566 |
| Sonnet 5 | $0.00003 | $0.00226 |
| Haiku 4.5 | $0.00001 | $0.00113 |
Grade A, and why
status 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 9d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
adaptive-harness-status
Display the current state of the adaptive-harness pool including harness performance statistics, pool membership, recent evaluation history, and pending evolution proposals.
Execution Steps
Step 1: Read Pool State and Pipeline Mode
Read(".adaptive-harness/harness-pool.json")
Read(".adaptive-harness/config.yaml")
Bash("cat .adaptive-harness/.pipeline-mode 2>/dev/null || echo 'off'")
If .adaptive-harness/harness-pool.json does not exist:
adaptive-harness state directory is missing or broken.
It will be auto-initialized with --general defaults on the next session start.
Run /adaptive-harness:run <task> to trigger auto-initialization and start a pipeline run.
Step 2: Read Recent Evaluation Logs
Scan .adaptive-harness/sessions/ for the most recent 10 evaluation files across all sessions:
Glob(".adaptive-harness/sessions/*/eval-*.json")
Read each and extract: harness name, overall score, timestamp, quality gate pass/fail.
Also check for pending evolution proposals:
Glob(".adaptive-harness/evolution-proposals/*.json")
Step 3: Display Status
Format and display the full status report:
═══════════════════════════════════════════════
ADAPTIVE-HARNESS STATUS
Project: {domain}
Pipeline mode: {auto|run|off}
Pool initialized: {initialized_at}
═══════════════════════════════════════════════
STABLE POOL ({N} harnesses)
┌─────────────────────────┬────────┬────────┬──────────┬────────────┐
│ Harness │ Weight │ Runs │ Score │ Last Run │
├─────────────────────────┼────────┼────────┼──────────┼────────────┤
│ tdd-driven │ 1.02 │ 16 │ 0.87 │ 2026-03-14 │
│ systematic-debugging │ 0.98 │ 12 │ 0.81 │ 2026-03-13 │
│ rapid-prototype │ 1.05 │ 22 │ 0.91 │ 2026-03-14 │
│ careful-refactor │ 0.95 │ 11 │ 0.78 │ 2026-03-12 │
│ research-iteration │ 1.00 │ 5 │ 0.84 │ 2026-03-10 │
│ code-review │ 1.01 │ 19 │ 0.88 │ 2026-03-14 │
│ migration-safe │ 0.99 │ 7 │ 0.83 │ 2026-03-11 │
└─────────────────────────┴────────┴────────┴──────────┴────────────┘
EXPERIMENTAL POOL ({N} harnesses)
(none) — Add custom harnesses to harnesses/ to see them here.
RECENT EVALUATIONS (last 10)
2026-03-14 14:32 tdd-driven 0.89 PASS "Fix auth login bug"
2026-03-14 11:15 rapid-prototype 0.93 PASS "Add dark mode toggle"
2026-03-13 16:44 careful-refactor 0.76 PASS "Extract shared utils"
...
EVOLUTION PROPOSALS
{N pending proposals — run /adaptive-harness:evolve to review}
OR
No pending proposals.
CONFIGURATION
Domain: {domain}
Pipeline mode: {auto|run|off}
Ensemble mode: {auto|always|never}
Evolution: {enabled (threshold: N successes) | disabled}
Config file: .adaptive-harness/config.yaml
PIPELINE MODE INFO
auto — All tasks auto-routed (using-adaptive-harness active)
run — One-shot /adaptive-harness:run in progress
off — No auto-routing (use /adaptive-harness:run for explicit runs)
Toggle: printf 'auto' > .adaptive-harness/.pipeline-mode (enable)
rm -f .adaptive-harness/.pipeline-mode (disable)
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.
- 9d ago First seen · 115 lines · 13 tokens per session scan A 0b85eea99139
status is a command published in the GitHub repository SeongwoongCho/adaptive-harness (8 stars, last pushed 5mo ago), licensed MIT. It adds 13 tokens to every session and 1,131 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.