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/KimYx0207/Meta_KimWrote 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/kimyx0207/meta_kim/meta-theory-verify)<a href="https://agentmods.dev/commands/kimyx0207/meta_kim/meta-theory-verify"><img src="https://agentmods.dev/badge/commands/kimyx0207/meta_kim/meta-theory-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/kimyx0207/meta_kim/meta-theory-verify"><img src="https://agentmods.dev/badge/commands/kimyx0207/meta_kim/meta-theory-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 | $0.00008 | $0.00265 |
| Opus 5 | $0.00004 | $0.00133 |
| Sonnet 5 | $0.00002 | $0.00053 |
| Haiku 4.5 | $0.00001 | $0.00026 |
Grade A, and why
meta-theory-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 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.
What it actually says
Run Meta_Kim verification from the rendered Meta_Kim package root. Choose the lightest route that matches the change risk:
smoke: prompt, docs, changelog, or narrow governance wording.global: global hooks, runtime homes, command sync, or install/update wiring.release: install/update, hooks, runtime matrix, provider registry, dependency compatibility, or explicitly release-grade work.
Default to smoke when no argument is provided.
npm --prefix "__META_KIM_PACKAGE_ROOT__" run meta:release:smoke
git -C "__META_KIM_PACKAGE_ROOT__" diff --check
For global, also run:
npm --prefix "__META_KIM_PACKAGE_ROOT__" run meta:check:global:release -- --targets claude,codex,cursor
For release, run:
npm --prefix "__META_KIM_PACKAGE_ROOT__" run meta:verify:all
Return the exact command results and keep proof layers separate: smoke pass, global-hook pass, graph freshness, and release-grade pass are not the same claim.
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 · 36 lines · 8 tokens per session scan A e25df744a416
meta-theory-verify is a command published in the GitHub repository KimYx0207/Meta_Kim (273 stars, last pushed yesterday), licensed Apache-2.0. It adds 8 tokens to every session and 265 once invoked, about $0.0000 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
sdd-verify
Validate implementation matches specs, design, and tasks.
ijfw-verify
Run the IJFW workflow Verify phase (Deep D5). Full audit against the original brief. Usage: /ijfw-verify.
ijfw-audit
Run the IJFW audit gate for the current workflow phase. Usage: /ijfw-audit [phase name].
ai-feature-eval-harness
Design an evaluation plan for a product AI feature (LLM- or model-backed output): measurable success criteria, a held-out labeled eval dataset shape, per-criterion grading (code-based first, then LLM-based for nuanced judgment), and a pass threshold, then persist as AIEVALPLAN.md. Use when the task ships or changes a…
implement-approved-slice
Implement only the approved slice with minimal, explicit, review-friendly changes, then persist execution evidence in slice notes and TASKSTATE.md. The single official execution path of the workflow. Supports an opt-in test-first (TDD) mode, enabled per slice or via --tdd, that writes the failing test before the code…
api-runtime-verify
Verify an implemented backend HTTP surface at runtime: per route, record the request actually made, the HTTP status, the response content-type, and the observed body shape, assert each response against the slice's acceptance behavior, classify the findings, and decide a PASS/FAIL/BLOCKED runtime gate. The probe's real…