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.
npx skills add MadGraphTeam/MadAgents --skill mg-deep-verifygit clone --depth 1 https://github.com/MadGraphTeam/MadAgentsWrote 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/skills/madgraphteam/madagents/mg-deep-verify)<a href="https://agentmods.dev/skills/madgraphteam/madagents/mg-deep-verify"><img src="https://agentmods.dev/badge/skills/madgraphteam/madagents/mg-deep-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/skills/madgraphteam/madagents/mg-deep-verify"><img src="https://agentmods.dev/badge/skills/madgraphteam/madagents/mg-deep-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 | $0.00070 | $0.03926 |
| Opus 5.5 | $0.00028 | $0.01570 |
| Sonnet 5.5 | $0.00014 | $0.00785 |
| Haiku 4.5 | $0.00007 | $0.00393 |
Grade A, and why
mg-deep-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.
How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mg-deep-verify
Seven stages. Stages 1-5 run per invocation; Stage 6 (re-verify) fires only on a revision and is capped (below); Stage 7 (failure-mode extraction) is off the answer path — after the answer is composed, on a non-clean cascade only, never blocking.
Verification prefers acting over reasoning — where a claim is checkable by running, it goes to the probe (Stage 4); a reasoning-only check confirms "looks right," not "runs right." The probe is the load-bearing lens the reasoning stages scope and aggregate around.
Dispatch discipline
Every Agent dispatch you make within this skill — Stage 1 (the regime-review dispatch), Stage 2 (the per-claim verifier dispatches), Stage 3, Stage 6, Stage 7, the synthesis-verification step in Stage 5, and any other dispatch the cascade triggers — must include this line verbatim in the dispatch prompt:
Deep-verify dispatch: wiki and Recent lessons as orientation only; walk source adversarially for THIS input even when a wiki page's scope matches or your MEMORY.md's Recent lessons say you've seen this before.
This overrides the adopt-a-cached-page discipline on the dispatched agent's own card. The cascade is doing the verification; the dispatched agent must not shortcut via cached wiki content or cached lessons. Each stage's dispatch instructions below repeat the cue at the point of action — do not omit it.
You apply the same self-discipline. When you are running this cascade, your own lead-memory's Recent lessons and playbook references are orientation only — usable to route and prioritise, not citable as verified evidence in the synthesis. Source-walk via consultant dispatches (carrying the line above) for THIS input.
When Stage 4 invokes /mg-probe, attach the same line to the ma-probe dispatch the skill makes on your behalf. The /mg-probe skill is callable outside the cascade (where this discipline does not apply); the mg-deep-verify line is your channel for opting that dispatch into adversarial mode.
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 · 161 lines · 70 tokens per session scan A 5fb382586286
mg-deep-verify is a skill published in the GitHub repository MadGraphTeam/MadAgents (14 stars, last pushed 2mo ago), licensed MIT. It adds 70 tokens to every session and 3,926 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
train-pose
Train/evaluate WiFi pose models honestly — camera-supervised (MediaPipe + CSI) and camera-free (WiFlow), always checked against the mean-pose baseline before any PCK is quoted.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
experiment-audit
A review step that checks whether an experiment's reported results are supported by real data and a sufficiently broad test.
i4h-catheter-navigation-e2e
End-to-end smoke for catheter navigation covering setup, digital twin, DRR, and unit tests. Use when asked to run the full catheter workflow smoke or demo the v0.7 pipeline.
i4h-catheter-navigation-render-drr
Render a single DRR fluoroscopy frame from a CT cache or synthetic phantom. Use when asked to render DRR, generate a fluoro image, or smoke-test the Slang renderer.
i4h-catheter-navigation-smoke
Run CPU-only fluorosim smoke tests (imports, preprocessing, CLI parsers). Use when asked to smoke-test catheter navigation in CI or without a GPU.