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/verify)<a href="https://agentmods.dev/commands/vitaliikapliuk/modelharness/verify"><img src="https://agentmods.dev/badge/commands/vitaliikapliuk/modelharness/verify/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/verify"><img src="https://agentmods.dev/badge/commands/vitaliikapliuk/modelharness/verify.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 | $0.00018 | $0.00188 |
| Opus 5.5 | $0.00007 | $0.00075 |
| Sonnet 5.5 | $0.00004 | $0.00038 |
| Haiku 4.5 | $0.00002 | $0.00019 |
Grade A, and why
verify 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 1mo 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
Verify the most recent substantial piece of work in this session (or, if $ARGUMENTS names a scope, verify that instead).
- Collect: the original specification / request, the definition-of-done checks, and
the current state (run
git diff/git statusif the work is in a repo; otherwise list the produced artifacts). - Dispatch the
modelharness:verifieragent with all of the above. Ask it to verify independently — run the checks itself, not trust your summary. - Report its verdict to the user verbatim in structure: confirmed / gaps found / not verifiable. If gaps were found, propose fixes but do not apply them without the user's go-ahead unless the session was already running autonomously.
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.
- 1mo ago First seen · 16 lines · 18 tokens per session scan A 873a625f42be
verify is a command published in the GitHub repository vitaliikapliuk/modelharness (30 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 188 once invoked, about $0.0001 per session on Opus 5.5. 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
init
Install the formatters this repository needs, with every command visible before it runs.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
santa-loop
Adversarial dual-review convergence loop — two independent model reviewers must both approve before code ships.
extend
Capture a mid-PR sub-idea and implement it onto the current open PR's branch — no new branch, no new PR. Preserves Verify → Review → Deliver.
fec-smell
Diagnose frontend code smells with evidence and candidate refactorings without changing business code.
security-review
Depth-first security audit of the current git diff — OWASP Top 10, secret leakage, insecure-by-default APIs, and language-specific foot-guns. Pass a PR number to audit a specific PR's diff.