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.
git clone --depth 1 https://github.com/hellowind777/helloagentsWrote 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/plugins/hellowind777/helloagents/gemini-extension)<a href="https://agentmods.dev/plugins/hellowind777/helloagents/gemini-extension"><img src="https://agentmods.dev/badge/plugins/hellowind777/helloagents/gemini-extension/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/plugins/hellowind777/helloagents/gemini-extension"><img src="https://agentmods.dev/badge/plugins/hellowind777/helloagents/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
helloagents 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
60 files beside gemini-extension.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/dogdoing/complete.wav 668 KB
- assets/dogdoing/confirm.wav 200 KB
- assets/dogdoing/error.wav 256 KB
- assets/dogdoing/idle.wav 176 KB
- assets/dogdoing/warning.wav 176 KB
- assets/icons/icon-large.png 94 KB
- assets/icons/icon.png 8.2 KB
- assets/sounds/complete.wav 78 KB
- assets/sounds/confirm.wav 96 KB
- assets/sounds/error.wav 85 KB
- assets/sounds/idle.wav 81 KB
- assets/sounds/warning.wav 72 KB
- scripts/advisor-state.mjs 6.0 KB runs code
- scripts/capability-registry.mjs 3.0 KB runs code
- scripts/cli-branch.mjs 3.7 KB runs code
- scripts/cli-codex-backup.mjs 2.3 KB runs code
- scripts/cli-codex-config.mjs 12 KB runs code
- scripts/cli-codex-goals.mjs 3.1 KB runs code
- scripts/cli-codex-hooks-state.mjs 8.5 KB runs code
- scripts/cli-codex.mjs 12 KB runs code
- scripts/cli-config.mjs 1.5 KB runs code
- scripts/cli-cursor.mjs 1.0 KB runs code
- scripts/cli-doctor-codex.mjs 24 KB runs code
- scripts/cli-doctor-render.mjs 2.9 KB runs code
- scripts/cli-doctor.mjs 29 KB runs code
- scripts/cli-grok.mjs 1.5 KB runs code
- scripts/cli-host-detect.mjs 6.7 KB runs code
- scripts/cli-hosts.mjs 2.6 KB runs code
- scripts/cli-lifecycle-hosts.mjs 21 KB runs code
- scripts/cli-lifecycle.mjs 10 KB runs code
- scripts/cli-messages.mjs 11 KB runs code
- scripts/cli-process.mjs 699 B runs code
- scripts/cli-runtime-carrier.mjs 472 B runs code
- scripts/cli-runtime-root.mjs 12 KB runs code
- scripts/cli-toml-values.mjs 470 B runs code
- scripts/cli-toml.mjs 6.7 KB runs code
- scripts/cli-utils.mjs 8.2 KB runs code
- scripts/closeout-state.mjs 5.5 KB runs code
- scripts/cursor-hook.mjs 5.7 KB runs code
- scripts/delivery-gate-messages.mjs 2.9 KB runs code
- scripts/delivery-gate.mjs 6.3 KB runs code
- scripts/guard-rules.mjs 6.5 KB runs code
- scripts/guard.mjs 5.5 KB runs code
- scripts/notify-closeout.mjs 7.6 KB runs code
- scripts/notify-context.mjs 8.2 KB runs code
- scripts/notify-events.mjs 640 B runs code
- scripts/notify-gates.mjs 2.7 KB runs code
- scripts/notify-payload.mjs 2.0 KB runs code
- scripts/notify-route.mjs 3.7 KB runs code
- scripts/notify-shared.mjs 992 B runs code
- scripts/notify-sound.mjs 2.6 KB runs code
- scripts/notify-source.mjs 1.4 KB runs code
- scripts/notify-ui.mjs 5.9 KB runs code
- scripts/notify.mjs 20 KB runs code
- scripts/plan-contract.mjs 7.0 KB runs code
- scripts/project-session-cleanup.mjs 5.2 KB runs code
- scripts/project-storage.mjs 9.3 KB runs code
- scripts/qa-review-state.mjs 9.2 KB runs code
- scripts/ralph-loop.mjs 10 KB runs code
- scripts/replay-state.mjs 3.3 KB runs code
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 First seen · 9 lines scan A 93e119c21f41
helloagents is a plugin published in the GitHub repository hellowind777/helloagents (706 stars, last pushed 1mo ago), with no licence file. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-07.
Other plugins, from other repositories
causal-memory
Persistent causal memory for Claude Code — decisions, outcomes, and lessons that survive compaction. Same-context counterfactuals (natural experiments), a falsifiable prediction ledger, and an activation skill that teaches when to recall and record.
dsh
A bridge plugin connecting Claude Code with DeepSeek Harness, another coding-agent system. It provides commands for importing sessions, reviewing changes, critiquing designs, and delegating tasks.
blast-radius
See what a risky command would change before it runs.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
themes-example
themes-example. An open-source AI agent that brings the power of Gemini directly into your terminal.