Borrowing it
Nothing to install: this file belongs to Dimkox/adaptive-grok-build-pro. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Dimkox/adaptive-grok-build-pro/main/.agents/skills/verification-evidence/SKILL.mdgit clone --depth 1 https://github.com/Dimkox/adaptive-grok-build-proWrote 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/dimkox/adaptive-grok-build-pro/verification-evidence)<a href="https://agentmods.dev/skills/dimkox/adaptive-grok-build-pro/verification-evidence"><img src="https://agentmods.dev/badge/skills/dimkox/adaptive-grok-build-pro/verification-evidence/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/dimkox/adaptive-grok-build-pro/verification-evidence"><img src="https://agentmods.dev/badge/skills/dimkox/adaptive-grok-build-pro/verification-evidence.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 | $0.00027 | $0.00310 |
| Opus 5.5 | $0.00011 | $0.00124 |
| Sonnet 5.5 | $0.00005 | $0.00062 |
| Haiku 4.5 | $0.00003 | $0.00031 |
Grade A, and why
verification-evidence 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
Verification and Evidence
Run python scripts/grok_verify.py --mode pr. Verification receipts include a repository fingerprint. Any subsequent change makes them stale.
Dispatch every review agent selected by the route. Each must inspect the actual final tree and return the complete report to the coordinator out-of-band. The coordinator persists all reports in the change package after all reviews finish, then reruns final verification. Record passing reports with scripts/grok_review.py. Completion requires zero gaps in python scripts/grok_status.py.
Code and test reviewers run bounded, change-relevant mutation probes only in a reviewer-owned private scratch copy outside the reviewed worktree. Keep the candidate unchanged; scratch must be below a trusted non-sticky parent with mode 0700 and reproduce the exact candidate, including relevant staged, unstaged, and untracked changes. Bind the report to HEAD and candidate tree fingerprint before/after. Unsafe scratch, an incomplete snapshot, or a changed fingerprint makes the result inconclusive/stale. Configured read-only mode is not an OS-enforced isolation boundary. Reports include scratch path, literal reviewed-tree-modified: no, executed claims, exact commands and concise output, killed/survived/inconclusive mutants, and unexecuted claims with reasons.
Never claim a command passed unless its current result is available. Never reuse review evidence from a different tree.
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 Changed · +2 lines 3d1af27c36f0
- 2mo ago First seen · 13 lines · 27 tokens per session scan A 0477bf734f6a
verification-evidence is a skill published in the GitHub repository Dimkox/adaptive-grok-build-pro (2 stars, last pushed 23d ago), licensed MIT. It adds 27 tokens to every session and 310 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 2026-08-31.
Other skills, from other repositories
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.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.