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 medy-gribkov/arcana --skill local-securitygit clone --depth 1 https://github.com/medy-gribkov/arcanaWrote 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/medy-gribkov/arcana/local-security)<a href="https://agentmods.dev/skills/medy-gribkov/arcana/local-security"><img src="https://agentmods.dev/badge/skills/medy-gribkov/arcana/local-security/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/medy-gribkov/arcana/local-security"><img src="https://agentmods.dev/badge/skills/medy-gribkov/arcana/local-security.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 | $0.00033 | $0.01872 |
| Opus 5 | $0.00016 | $0.00936 |
| Sonnet 5 | $0.00007 | $0.00374 |
| Haiku 4.5 | $0.00003 | $0.00187 |
Grade C, and why
local-security scanned grade C with 4 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.
Enumerates the file system for secretsmediumData exfiltration
Searching home directories for .env, .ssh, .aws or credential files is reconnaissance for credential theft.
find ~ -maxdepth 3 -name ".netrc" -o -name ".npmrc" -o -name "credentials" \ Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
chmod 700 ~/.ssh Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Reaches for credential filesmediumPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
ssh-keygen -t ed25519 -C "github@workstation" -f ~/.ssh/id_ed25519_github Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -H "Authorization: token $GITHUB_TOKEN" https://api.github.com/user How it starts
The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Treat the developer workstation as a critical supply chain node. A compromised dev machine means compromised code, credentials, and infrastructure access. Follow these workflows to harden each surface.
SSH Hardening Workflow
- Generate an Ed25519 key per service. One key for GitHub, another for production servers, another for cloud.
- Protect the private key with a passphrase. Load it into
ssh-agentso you type it once. - Lock permissions on the
.sshdirectory and all key files. - Configure
~/.ssh/configto use ProxyJump instead of agent forwarding. - Rotate keys annually. Remove old public keys from every authorized service.
# Step 1: Generate a dedicated key
ssh-keygen -t ed25519 -C "github@workstation" -f ~/.ssh/id_ed25519_github
# Step 2: Add to agent with passphrase caching
ssh-add ~/.ssh/id_ed25519_github
# Step 3: Lock permissions
chmod 700 ~/.ssh
chmod 600 ~/.ssh/id_ed25519_*
chmod 644 ~/.ssh/*.pub
# Step 5: Verify fingerprint before trusting a key
ssh-keygen -l -f ~/.ssh/id_ed25519_github.pub
BAD - Single key reused everywhere, no passphrase, open permissions:
ssh-keygen -t rsa -b 2048 -N "" -f ~/.ssh/id_rsa
chmod 755 ~/.ssh
# Same key added to GitHub, AWS, production bastion, personal VPS
GOOD - Dedicated Ed25519 key, passphrase, tight permissions:
ssh-keygen -t ed25519 -C "github@workstation" -f ~/.ssh/id_ed25519_github
chmod 700 ~/.ssh
chmod 600 ~/.ssh/id_ed25519_github
BAD - Agent forwarding to untrusted host:
Host bastion
HostName bastion.example.com
ForwardAgent yes
GOOD - ProxyJump through bastion, no agent exposure:
Host bastion
HostName bastion.example.com
Host production
HostName 10.0.1.50
ProxyJump bastion
Windows OpenSSH Agent Setup
# Enable and start the agent service (persists across reboots)
Get-Service ssh-agent | Set-Service -StartupType Automatic
Start-Service ssh-agent
# Add key once
ssh-add $HOME\.ssh\id_ed25519_github
# Point Git to Windows OpenSSH instead of bundled ssh
git config --global core.sshCommand "C:/Windows/System32/OpenSSH/ssh.exe"
# Verify
ssh-add -l
What ships with it
1 file 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.
- 9d ago First seen · 215 lines · 33 tokens per session scan C a5320f7f54ed
local-security is a skill published in the GitHub repository medy-gribkov/arcana (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 1,872 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 4 findings (enumerates the file system for secrets, asks for root, reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
hue
Meta-skill that generates new design language skills. Works on Claude Code and Codex. Use when the user says 'create a design skill', 'generate design language', 'new design system skill', 'design skill inspired by X', 'design skill from this screenshot', '/hue', or 'use hue'. Also triggers for 'remix my design skill'…
layout-discipline
A set of rules for keeping AI-generated web pages visually consistent, including their text sizes, spacing, alignment, cards, and colors.
ab-test-designer
Design and analyze A/B tests — sample sizes, significance testing, multiple comparisons, and results interpretation.
accessibility-checker
Audit and fix accessibility issues — WCAG 2.2 compliance, ARIA labels, color contrast, keyboard navigation, and screen-reader compatibility.
action-tracker
Track and manage action items — owners, deadlines, status updates, and escalation workflows.
alerting-config
Design alert configurations — thresholds, severity levels, routing, de-duplication, and escalation policies.