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 agentmods add skills/qsong-github/drugclaw/nsidesnpx skills add QSong-github/DrugClaw --skill nsidesgit clone --depth 1 https://github.com/QSong-github/DrugClawWrote 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/qsong-github/drugclaw/nsides)<a href="https://agentmods.dev/skills/qsong-github/drugclaw/nsides"><img src="https://agentmods.dev/badge/skills/qsong-github/drugclaw/nsides.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 | $0.00054 | $0.01086 |
| Opus 5 | $0.00027 | $0.00543 |
| Sonnet 5 | $0.00011 | $0.00217 |
| Haiku 4.5 | $0.00005 | $0.00109 |
Grade A, and why
nsides-query 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 4d 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
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
5 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.
- 4d ago First seen · 85 lines · 54 tokens per session scan A bf48261add72
nsides-query is a skill published in the GitHub repository QSong-github/DrugClaw (116 stars, last pushed 9d ago), with no licence file. It adds 54 tokens to every session and 1,086 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 2026-08-30.
Other skills, from other repositories
start-experiment
Start the autoresearch optimization loop for a specific model + lane. Resolves the hierarchical program.md (root → model → lane), asks the user for hardware (local TPU VM or GKE cluster of a specified TPU type + topology), discovers available clusters from .env/, checks occupancy with USERPREFIX-aware attribution…
stop-experiment
Stop the autoresearch optimization loop cleanly. Disarms the launch-armed process watcher, cancels pending wakeups, reaps orphan workloads on the project's cluster pool, files any missing experiment pages, runs lint, and appends a clean-shutdown marker to wiki/log.md. Invoke at the end of an autoresearch session.
create-experiment
Bootstrap a new model family for the autoresearch loop. Creates the folder structure under wiki/experiments/, scaffolds the model-level program.md from a template (asking the user about lanes, sizes, hardware targets, sequence length, and architecture invariants), optionally creates lane-level program.md stubs, and…
edit-model-code
Coding-discipline guidelines for surgically modifying model code inside a per-experiment fork in the autoresearch loop. Adapts Andrej Karpathy's LLM-coding guidelines (think before coding, simplicity first, surgical changes, goal-driven execution) to this project's invariants — no semantics drift, one mechanism per…
author-kernel
Authoring discipline for kernel-family candidates (the author role of kernelexperiments/program.md step K4). Load BEFORE writing any kernel candidate — whether you are a solo agent running the whole K0–K9 loop (production: Gemini / Claude / Codex from a bare prompt) or a dispatched author process in the trial…
formulate-kernel-hypothesis
Generate ONE structured kernel-optimization hypothesis — step K2 of wiki/kernelexperiments/program.md. Self-contained for the kernel lane (any harness, bare-prompt solo or dispatched): reads the K1 bound diagnosis + the kernel index's signal→lever map + the family's refuted layers, and returns a proposal with the…