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/doidor/agentrig/verify-loopnpx skills add doidor/agentrig --skill verify-loopgit clone --depth 1 https://github.com/doidor/agentrigWhat 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 | $0.00035 | $0.00434 |
| Opus 5 | $0.00017 | $0.00217 |
| Sonnet 5 | $0.00007 | $0.00087 |
| Haiku 4.5 | $0.00003 | $0.00043 |
Grade A, and why
verify-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 yesterday.
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
verify-loop (principle 5, generalized)
A reusable decision loop for converging on any verification signal before handoff. Generalizes the visual-self-verify pattern to builds, tests, CI runs, lint, or e2e.
Loop
- Trigger the check (or wait for the async one pinned to your own HEAD — never trust a stale result from an earlier commit).
- Inspect the result:
- Green / no unintended change → continue (proceed to review/handoff).
- Red / unintended change → go to step 3.
- Intended but human-gated change → self-park (see below). Do not iterate.
- Fix the root cause and re-run. Cap at N = 3 iterations (default).
- After N failures → stop iterating and take a recovery path: self-park with a precise note, or escalate. Do not loop indefinitely.
Self-park
When the right next step needs a human (low reversibility, an intended diff behind a human-only
gate, or repeated failure), leave a clear note describing what you saw and what you tried, move the
task to parked, and never apply the human-only label yourself.
Notes
- Pin every check to your current HEAD.
- Record any new gotcha in
.agents/wiki/. - This is the engine behind
self-verify; useverify-loopwhenever the signal is asynchronous.
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.
- yesterday First seen · 36 lines · 35 tokens per session scan A fd3d2d5b4dc6
verify-loop is a skill published in the GitHub repository doidor/agentrig (5 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 434 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…