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 sliamh11/Deus --skill add-understand-anythinggit clone --depth 1 https://github.com/sliamh11/DeusWrote 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/sliamh11/deus/add-understand-anything)<a href="https://agentmods.dev/skills/sliamh11/deus/add-understand-anything"><img src="https://agentmods.dev/badge/skills/sliamh11/deus/add-understand-anything/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/sliamh11/deus/add-understand-anything"><img src="https://agentmods.dev/badge/skills/sliamh11/deus/add-understand-anything.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 | $0.00078 | $0.01371 |
| Opus 5 | $0.00039 | $0.00685 |
| Sonnet 5 | $0.00016 | $0.00274 |
| Haiku 4.5 | $0.00008 | $0.00137 |
Grade C, and why
add-understand-anything scanned grade C with 2 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 9d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/Lum1104/Understand-Anything/main/install.sh | bash -s <platform> Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/Lum1104/Understand-Anything/main/install.sh | bash -s <platform> How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add Understand-Anything
This skill installs Understand-Anything
— an LLM-powered codebase-analysis tool that produces interactive knowledge
graphs, guided tours, and deep-dive explanations of any project. Once installed,
the agent gains the /understand* family of skills.
It ships as a Claude Code plugin distributed through a GitHub plugin
marketplace. This skill runs the whole marketplace flow (add marketplace →
install plugin → verify) end-to-end so a single /add-understand-anything
completely integrates it — no manual /plugin steps.
Backend note: This is a Claude Code installer. The
claude plugin …commands below only exist when Claude Code is the active backend (Deus's default). On non–Claude-Code backends (Codex, opencode, gemini, …) use the upstreaminstall.shfallback in Phase 0 instead.
Phase 0: Backend guard
Confirm the Claude Code CLI is available before doing anything else:
command -v claude >/dev/null 2>&1 && echo "claude CLI found" || echo "NO claude CLI"
If the claude CLI is not found, this backend can't use the plugin
marketplace. Stop here and tell the user to install via the upstream script
instead (it symlinks the skills into the right place for their runtime):
# Replace <platform> with one of: codex, opencode, gemini, pi, vscode, ...
curl -fsSL https://raw.githubusercontent.com/Lum1104/Understand-Anything/main/install.sh | bash -s <platform>
Then skip the rest of this skill.
Phase 1: Pre-flight (idempotent)
Check current state with the read-only list commands and branch on their
output — do not assume how the CLI handles a duplicate add/install.
Is the marketplace already added?
claude plugin marketplace list 2>/dev/null | grep -qF "Lum1104/Understand-Anything" \
&& echo "MARKETPLACE_PRESENT" || echo "MARKETPLACE_MISSING"
(Match the exact marketplace source Lum1104/Understand-Anything — list
prints it as Source: GitHub (Lum1104/Understand-Anything) — so an unrelated
plugin that merely contains the substring understand-anything can't trigger a
false MARKETPLACE_PRESENT.)
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.
- 9d ago First seen · 142 lines · 78 tokens per session scan C 3164086e44a3
add-understand-anything is a skill published in the GitHub repository sliamh11/Deus (51 stars, last pushed 3d ago), licensed MIT. It adds 78 tokens to every session and 1,371 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
memcord
Privacy-first, self-hosted chat memory for OpenClaw — save and recall conversation history across sessions without any cloud dependency.
roadmap-build
Build or repair a roadmap that agents can actually execute, not just read. Produces a single validated YAML source of truth, generated views, definitions of done with evidence kinds, a task pool linked on two axes, an idea intake queue, and three standing checks that keep it honest. Use when asked to "build a…
Research for Datacore
Automated research — source processing, podcast generation, and knowledge extraction.
GTD for Datacore
Getting Things Done — task capture, inbox processing, and org-mode management.
Outbox for Datacore
Content routing — archive to server, search archived content.
research-status
Check research queue counts, recent podcasts, knowledge base growth, and Readwise items.