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 griffinwork40/agent-afk --skill shadow-verifygit clone --depth 1 https://github.com/griffinwork40/agent-afkWrote 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/griffinwork40/agent-afk/shadow-verify)<a href="https://agentmods.dev/skills/griffinwork40/agent-afk/shadow-verify"><img src="https://agentmods.dev/badge/skills/griffinwork40/agent-afk/shadow-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/griffinwork40/agent-afk/shadow-verify"><img src="https://agentmods.dev/badge/skills/griffinwork40/agent-afk/shadow-verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00078 | $0.03423 |
| Opus 5.5 | $0.00031 | $0.01369 |
| Sonnet 5.5 | $0.00016 | $0.00685 |
| Haiku 4.5 | $0.00008 | $0.00342 |
Grade A, and why
shadow-verify scanned grade A with 1 finding 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 13d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Default to `subagent_type: "research-agent"` (mechanically locked to Read/Grep/Glob/WebFetch/WebSearch — cannot Edit/commit/push).** If the claim requires Bash to verify (running a failing test, `gh pr view`, `git lo Copies of this mod
1 near-identical copy found in the catalogue:
- shadow-verify — 100% identical, 63 lines differ
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sub-agent contract
/contract
When a sub-agent (or wave) returns investigation findings, code-review conclusions, audit claims, refactor plans, gap-analysis results, or counts that will drive user decisions or file changes, do NOT surface the report. Instead, run a shadow verification wave before merging.
Invocation modes
This skill has two invocation modes that share the same verifier machinery, normalization pre-flight, merge rules, gate logic, and composition-axis guard — but differ in scope and output shape.
Default mode (no flag): Sample 2–3 highest-stakes claims from a sub-agent's live output and verify them before surfacing the report. Optimized for latency — catches critical errors without blocking on exhaustive coverage.
--findings-list mode: Exhaustively verify every finding in a pre-existing findings document (a file path or inline text) before any downstream action phase is dispatched. Every finding 1–N must appear in the output checklist — no finding may be omitted or left blank. Produces a terminal gate verdict (VERIFIED / PARTIAL / BLOCKED) that controls whether a downstream action phase may proceed. Use this when an operator supplies a research-phase output and wants a completeness guarantee before committing to action.
Pre-flight: claim normalization and scale guard
Before dispatching any verifiers (in either mode), the coordinating agent normalizes each finding/claim to a canonical tuple:
[FINDING_ID] <subject> :: <predicate> :: <evidence_ref>
evidence_ref must be a concrete pointer — a file path, line number, git ref, config key, or API endpoint. Claims that cannot be anchored to a concrete evidence_ref are classified UNVERIFIABLE immediately and removed from the verification queue. They are preserved in the final output under a dedicated UNVERIFIABLE section with the reason they could not be anchored (no re-derivation sub-agent is dispatched for them).
Scale cap:
- Default mode: if the normalized claim list exceeds 50 items, the coordinating agent halts and asks the operator to scope the investigation before proceeding. Verification at scale degrades into noise; a 50-item cap prevents a finding flood from becoming an echo-chamber rubber-stamp.
--findings-listmode: if the normalized findings list exceeds 30 items, the orchestrator halts and asks the operator to scope before proceeding. Exhaustive verification is more expensive per item; a tighter cap prevents runaway fan-out.
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.
- 13d ago Changed · +43 lines · -58 tokens per session 23526494dffc
- 24d ago Changed · +1 lines d38252df942b
- 1mo ago First seen · 96 lines · 136 tokens per session scan A 9f7db5a0612c
shadow-verify is a skill published in the GitHub repository griffinwork40/agent-afk (61 stars, last pushed today), licensed Apache-2.0. It adds 78 tokens to every session and 3,423 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
md-audit
Read-only code quality audit — scan the current working directory for common issues (bugs, dead code, security hotspots, missing error handling) and return a prioritised findings report. No files are edited. Use when asked to "audit the code", "quick audit", "find issues", "code scan", or "what's wrong with this…
hqe
Comprehensive codebase health auditing, remediation, and verification skill based on the canonical HQE Protocol v5.0.0.
hunk-release
Prepares, publishes, verifies, and curates Hunk releases. Use for release metadata, benchmarks, tags, publishing, release videos, backports, or recovery.
printing-press-output-review
Internal sub-skill: agentic review of a printed CLI's sampled command output for plausibility issues that rule-based checks can't encode (substring-match relevance, format bugs, silent source drops, ranking failures). Invoked via the Skill tool by the main printing-press skill at Phase 4.85 and printing-press-polish…
brutal-honesty-review
Unvarnished technical criticism combining Linus Torvalds' precision, Gordon Ramsay's standards, and James Bach's BS-detection. Use when code/tests need harsh reality checks, certification schemes smell fishy, or technical decisions lack rigor. No sugar-coating, just surgical truth about what's broken and why.
cocoreview
CocoReview — structured code review with six-severity findings vocabulary, progressive disclosure architecture, and universal anti-pattern baseline. Invoked via $review [file] [--complexity] [--security] [--architecture] [--language ].