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/sodam-ai/SoDam-Loop-EngWrote 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/sodam-ai/sodam-loop-eng/sodam-loop-eng)<a href="https://agentmods.dev/plugins/sodam-ai/sodam-loop-eng/sodam-loop-eng"><img src="https://agentmods.dev/badge/plugins/sodam-ai/sodam-loop-eng/sodam-loop-eng/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/sodam-ai/sodam-loop-eng/sodam-loop-eng"><img src="https://agentmods.dev/badge/plugins/sodam-ai/sodam-loop-eng/sodam-loop-eng.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
sodam-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 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 it installs
The manifest is a name and a version. 9 skills, 9 commands, 1 agent, 4 hooks travel with it, and installing the plugin installs all of them — 878 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill sodam-loop-repair A 66 tokens
- Skill sodam-loop-start A 167 tokens
- Skill sodam-loop-help A 43 tokens
- Skill sodam-loop-checkup A 72 tokens
- Skill sodam-loop-install A 47 tokens
- Skill sodam-loop-status A 55 tokens
- Skill sodam-loop-tone A 50 tokens
- Skill sodam-loop-uninstall A 56 tokens
- Skill sodam-loop-undo A 39 tokens
- Command start A 46 tokens
- Command repair A 31 tokens
- Command uninstall A 29 tokens
- Command checkup A 25 tokens
- Command help A 24 tokens
- Command install A 17 tokens
- Command status A 19 tokens
- Command tone A 23 tokens
- Command undo A 22 tokens
- Agent checker A 47 tokens
- Hook PreToolUse A not measured
- Hook SessionStart A not measured
- Hook Stop A not measured
- Hook UserPromptSubmit A not measured
What ships with it
1 file beside plugin.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.
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 Changed dee855768cd4
- 1mo ago First seen · 6 lines scan A 03ae686a936c
sodam-loop is a plugin published in the GitHub repository sodam-ai/SoDam-Loop-Eng (2 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 2026-08-31.
Other plugins, from other repositories
sodam-harness
A safety add-on for people who are new to coding agents, with guidance in simple Korean. It can guard risky work with confirmation, backups, and undo support.
auto-cc
Automatic tool-call review for Claude Code. A local encoder scores every proposed tool call before it runs, approving safe work and blocking dangerous calls with an explanation the agent can act on.
thumbgate
One 👎 becomes a hard rule the agent cannot bypass. Captures thumbs-down feedback, distills it into PreToolUse Pre-Action Checks, enforced across every future Claude Code session.
claude-code-privacy-guard
Privacy guard plugin for Claude Code - prevents PII and secrets from leaking into AI prompts.
caushell-claude
Session-aware shell guardrails for Claude Code backed by the Caushell runtime.
agentguards
LLM security guardrails for Claude Code — jailbreak detection, prompt-injection and web-content scanning, data-exfiltration blocking, and destructive-command authorization. Enforced by hooks on every prompt, shell command, fetched page and file write. Never answers a permission prompt for you: it blocks or asks, and…