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 dinglebear-ai/dendrite --skill scrutinygit clone --depth 1 https://github.com/dinglebear-ai/dendriteWrote 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/dinglebear-ai/dendrite/scrutiny)<a href="https://agentmods.dev/skills/dinglebear-ai/dendrite/scrutiny"><img src="https://agentmods.dev/badge/skills/dinglebear-ai/dendrite/scrutiny.svg" alt="Measured on agentmods" 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 | $0.00074 | $0.00577 |
| Opus 5 | $0.00037 | $0.00289 |
| Sonnet 5 | $0.00015 | $0.00115 |
| Haiku 4.5 | $0.00007 | $0.00058 |
Grade C, and why
scrutiny scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
| List monitored devices | `curl -sS "$SCRUTINY_URL/api/summary" \| python3 -c 'import sys,json;print(*json.load(sys.stdin)["data"]["summary"].keys(),sep="\n")'` | Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| Health | `curl -sS "$SCRUTINY_URL/api/health" -w '\nHTTP %{http_code}\n'` | The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
What ships with it
3 files beside SKILL.md 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.
- 7d ago First seen · 53 lines · 74 tokens per session scan C ff57884d81cd
scrutiny is a skill published in the GitHub repository dinglebear-ai/dendrite (1 stars, last pushed 11d ago), licensed AGPL-3.0. It adds 74 tokens to every session and 577 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 2026-08-31.
Other skills, from other repositories
lov-migrate-camera-media
A macOS workflow for copying photos and videos from a camera or memory card to an SSD. It preserves the card's directory structure and checks copied files with SHA-256 hashes, a way to compare exact file contents.
computer-vision-expert
SOTA Computer Vision Expert (2026). Specialized in YOLO26, Segment Anything 3 (SAM 3), Vision Language Models, and real-time spatial analysis.
it-infrastructure-equipment-selection
Portable IT infrastructure solution architect skill for selecting, sizing, validating and budgeting physical infrastructure equipment. Use for guided requirement discovery, scenario-based planning, equipment selection, BOM generation, tender/RFQ compliance and specification generation, project infrastructure planning…
ros-robotics
A guide for developing, moving, building, and debugging robot software with ROS 1 or ROS 2, the open-source frameworks commonly used to connect robot components.
arm-cortex-expert
Senior embedded software engineer specializing in firmware and driver development for ARM Cortex-M microcontrollers (Teensy, STM32, nRF52, SAMD). Decades of experience writing reliable, optimized, and maintainable embedded code with deep expertise in memory barriers, DMA/cache coherency, interrupt-driven I/O, and…
meteocontrol-assistant
Specialized assistant for monitoring and analyzing solar installations via the MeteoControl VCOM API. Use it to troubleshoot production drops, triage alerts, and generate system reports.