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 edible999999999-jpg/humhum --skill verifygit clone --depth 1 https://github.com/edible999999999-jpg/humhumWrote 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/edible999999999-jpg/humhum/verify)<a href="https://agentmods.dev/skills/edible999999999-jpg/humhum/verify"><img src="https://agentmods.dev/badge/skills/edible999999999-jpg/humhum/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/edible999999999-jpg/humhum/verify"><img src="https://agentmods.dev/badge/skills/edible999999999-jpg/humhum/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 | $0.00062 | $0.00697 |
| Opus 5 | $0.00031 | $0.00349 |
| Sonnet 5 | $0.00012 | $0.00139 |
| Haiku 4.5 | $0.00006 | $0.00070 |
Grade A, and why
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 12d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run the quality gate suite for HUMHUM, but only for the gates that cover files changed in the current diff. This mirrors what CI checks (frontend typecheck + Rust fmt/clippy/test) plus the frontend unit tests.
1. Diff-aware check selection
First determine which gates are actually affected by the current change.
git diff --name-only origin/main...HEAD
If that fails (no upstream branch), fall back to:
git diff --name-only HEAD
A gate is affected when at least one changed file matches its pattern:
- Frontend typecheck:
src/**,package*.json,tsconfig.json,vite.config.ts,tailwind.config.js,postcss.config.js,index.html - Frontend unit tests (vitest / node --test):
src/**/*.test.{ts,tsx},scripts/*.test.mjs,relay/**/*.test.mjs, pluspackage*.json,vite.config.ts,vitest.config.* - Rust backend (fmt / clippy / test):
src-tauri/**,Cargo.toml,Cargo.lock
Report which gates were selected and why. If no gate matches the diff (for example, only docs, design assets, .github/workflows, or skill markdown changed), report that no quality gates are needed for this diff and stop. Do not run the full suite unnecessarily.
2. Run selected gates
For each selected gate, run the commands below from the repo root. Do not stop at the first failure unless a step cannot proceed — collect results from every selected step so you can report all problems at once.
Frontend typecheck (selected when frontend source/config changed)
npx tsc --noEmit
Frontend unit tests (selected when a frontend or scripts test file changed)
npm test
Rust checks (selected when Rust source/config changed; run inside src-tauri/)
cd src-tauri && cargo fmt --check && cargo clippy --locked -- -D warnings && cargo test --lib
3. Summarize
Report each selected gate as pass/fail, and for any failure show the specific error(s) and the file/line. If no gates were selected, say so concisely and explain which files changed. If everything selected passes, say so concisely.
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.
- 12d ago First seen · 61 lines · 62 tokens per session scan A 2894ecf83c5d
verify is a skill published in the GitHub repository edible999999999-jpg/humhum (1 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 697 once invoked, about $0.0003 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
rust-testing
Design Rust tests that catch real regressions — unit, integration, doc, property, snapshot, and golden tests, and differential tests that prove a port matches its source. Use when writing or reviewing Rust tests, when a change lands without tests, when deciding what form a test should take, when a port needs parity…
java-unit-test
A code-generation guide for Java unit tests in Spring Boot projects. Unit tests check one small piece of code in isolation; Spring Boot is a Java framework for building web applications and services.
typescript
TypeScript strict mode with eslint and jest.
cpp-testing
A guide for testing C++17/20 code with GoogleTest, GoogleMock, CMake, and CTest. It covers unit and integration tests, test discovery, coverage, and sanitizers.
perl-testing
Perl testing patterns using Test2::V0, Test::More, prove runner, mocking, coverage with Devel::Cover, and TDD methodology.
rust-development
Idiomatisk Rust-utvikling med cargo, clippy, error handling, async/tokio, unsafe og testing.