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 agentmods add skills/rexleimo/aios/verification-loopnpx skills add rexleimo/aios --skill verification-loopgit clone --depth 1 https://github.com/rexleimo/aiosWhat 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 | $0.00032 | $0.00945 |
| Opus 5 | $0.00016 | $0.00473 |
| Sonnet 5 | $0.00006 | $0.00189 |
| Haiku 4.5 | $0.00003 | $0.00094 |
Grade A, and why
verification-loop 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 2d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verification Loop
Trigger
Use this skill when:
- You changed runtime behavior (scripts, wrappers, MCP server, install flows)
- You are about to say "done", "fixed", "works", or "passes"
- You are about to bump version / release
Rules
- Prefer commands with deterministic exit codes over "it looks fine".
- If you cannot run verification, say exactly what you could not run and why.
Baseline Checks (AIOS)
-
Run the verifier:
aios doctor- Or:
node scripts/aios.mjs doctor - Compatibility wrappers:
scripts/verify-aios.sh/scripts/verify-aios.ps1
-
MCP server changes (minimum):
cd mcp-server && npm run typecheckcd mcp-server && npm run build- Manual smoke:
chrome.launch_cdp->browser.connect_cdp->page.goto->page.extract_text/page.screenshot->browser.close
-
Install/wrapper changes:
- Re-run install/update on a clean-ish shell session.
- Confirm new commands are visible and resolve to
ROOTPATHscripts.
Evidence Capture
- Record the exact commands run and whether they succeeded.
- For failures: include the first actionable error line and the remediation you applied.
Structured Verdict Schema
Inspired by the-pair v2.0.2 quality_gate.rs: every completion claim MUST be
backed by a structured verdict with exactly four sections. A verdict missing any
section is an automatic REJECT — there is no partial credit.
The four required sections, in order:
- FILES_REVIEWED — list of files reviewed with line ranges and change status.
- CHECKS — typecheck, test suite, lint — each with a concrete PASS/FAIL status.
- CODE — the specific code snippet or issue reference, as a quoted block.
- VALIDATION — summary verdict:
APPROVEDorREJECTED, followed by specificnext_actionswhen rejected.
Mandatory format
VERDICT:
FILES_REVIEWED:
- path/to/file.ts: lines 45-67 (changed)
CHECKS:
- typecheck: PASS
- test suite: PASS (8/8)
- lint: PASS
CODE:
> // specific snippet or issue reference
VALIDATION:
APPROVED — all checks pass
OR
REJECTED — [specific next_actions list]
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.
- 2d ago First seen · 102 lines · 32 tokens per session scan A 16cd990ddd02
verification-loop is a skill published in the GitHub repository rexleimo/aios (52 stars, last pushed 3d ago), licensed MIT. It adds 32 tokens to every session and 945 once invoked, about $0.0002 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 skills, from other repositories
arxiv
Standardized arXiv skill for MediaUse. Includes Windows install, key onboarding, strict context/auth flow, full arXiv dynamic command map, and safety/rate controls.
douyinv2
Standardized douyinv2 skill for MediaUse. Includes Windows install, key onboarding, strict context/auth flow, full douyinv2 dynamic command map, and safety/rate controls.
Use when handling MediaUse LinkedIn automation tasks, including jobs and people search, timeline and inbox retrieval, profile reads, safe connect/message flows, and Sales Navigator workflows, with Windows install, key onboarding, strict context/auth flow, full dynamic command map, and safety/rate controls.
xiaohongshu
Standardized Xiaohongshu skill for MediaUse. Includes Windows install, key onboarding, strict context/auth flow, full Xiaohongshu dynamic command map, and safety/rate controls.
chatgpt
Standardized ChatGPT skill for MediaUse. Includes Windows install, key onboarding, strict context/auth flow, full ChatGPT dynamic command map, and safety/rate controls.
fifa2026
Standardized fifa2026 skill for MediaUse. Includes Windows install, key onboarding, strict context/auth flow, full fifa2026 dynamic command map, and safe read-oriented execution controls.