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/vitaliikapliuk/modelharnessWrote 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/vitaliikapliuk/modelharness/goal)<a href="https://agentmods.dev/commands/vitaliikapliuk/modelharness/goal"><img src="https://agentmods.dev/badge/commands/vitaliikapliuk/modelharness/goal/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/vitaliikapliuk/modelharness/goal"><img src="https://agentmods.dev/badge/commands/vitaliikapliuk/modelharness/goal.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 | $0.00035 | $0.00214 |
| Opus 5 | $0.00017 | $0.00107 |
| Sonnet 5 | $0.00007 | $0.00043 |
| Haiku 4.5 | $0.00003 | $0.00021 |
Grade A, and why
goal 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.
What it actually says
The user wants to start a substantial task. Do NOT start working yet.
- Read their request: $ARGUMENTS (if empty, ask what they want to build).
- Interview briefly — one question at a time, only for genuinely missing pieces:
- Goal: what outcome, for whom, why now?
- Constraints: stack, style, what must NOT change, performance/compat limits?
- Definition of done: which binary checks prove completion (tests pass, command output, observable behavior)?
- Restate the complete specification in one block and get a quick confirmation.
- Execute the full task against that spec autonomously: follow the modelharness core (grounded progress, self-verification cadence, fresh-context verification before completion claims). Do not stop to ask about minor decisions — note them instead.
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 · 17 lines · 35 tokens per session scan A 5ad7a42326cd
goal is a command published in the GitHub repository vitaliikapliuk/modelharness (38 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 214 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 2026-08-30.
Other commands, from other repositories
create-task
Automatically scan a dbt project and generate ADE-Bench benchmark tasks via pattern matching.
plan-tasks
Interactively plan and generate ADE-Bench benchmark tasks from a dbt project (recommended).
setup
Install or verify the ADE-Bench harness at /.ade-bench (clones repo, installs CLI, downloads bundled DuckDB databases).
done
Archive the current plan after completion.
status
Show current ADE build progress and evaluator scores.
check-dev
Type-check a Z specification with fuzz.