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 Soul-Brews-Studio/arra-oracle-skills-cli --skill gogit clone --depth 1 https://github.com/Soul-Brews-Studio/arra-oracle-skills-cliWrote 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/soul-brews-studio/arra-oracle-skills-cli/go)<a href="https://agentmods.dev/skills/soul-brews-studio/arra-oracle-skills-cli/go"><img src="https://agentmods.dev/badge/skills/soul-brews-studio/arra-oracle-skills-cli/go/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/soul-brews-studio/arra-oracle-skills-cli/go"><img src="https://agentmods.dev/badge/skills/soul-brews-studio/arra-oracle-skills-cli/go.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 311 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- medium Data Exfiltration · line 223 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 342 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 374 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Excessive Agency · line 505 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00066 | $0.05713 |
| Opus 5 | $0.00033 | $0.02857 |
| Sonnet 5 | $0.00013 | $0.01143 |
| Haiku 4.5 | $0.00007 | $0.00571 |
Grade B, and why
go scanned grade B with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
count=$(grep -rl "/$skill" ~/.claude/projects/*/*.jsonl 2>/dev/null | wc -l) Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
LATEST=$(curl -s https://api.github.com/repos/Soul-Brews-Studio/arra-oracle-skills-cli/tags | grep -m1 '"name"' | cut -d'"' -f4) Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
subprocess.run(['git', '-C', repo, 'fetch', '--quiet', 'origin'], check=False) How it starts
The opening of the file, as written. The whole thing — 513 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/go
Switch gear. Single source of truth.
Usage
/go # all skills — profile tier + installed status
/go list # same as /go (no args)
/go minimal # newcomer essentials (7 skills, default)
/go standard # daily driver (13 skills)
/go full # all stable (excludes lab-only experiments)
/go lab # everything including experimental
/go cleanup # remove ALL skills → fetch latest → fresh install
/go update # check for new version + upgrade in-place
/go install team-agents # cherry-pick install specific skills
/go remove watch # uninstall specific skills
/go find feel # search all available skills by name
⚠ NEW (#285):
/go <profile>now ALIGNS your installed skills to the target profile. arra-managed skills NOT in the target profile will be removed. External / non-arra skills are never touched. A pre-removal diff is shown before any deletion occurs.
CLI Detection
Before running any command, detect the CLI path. It may not be in $PATH on all machines.
Two variables, because reading and writing have different safety requirements.
# $ARRA — READ-ONLY commands (profiles, list, --version). The local binary is fine
# here: it is fast, and a slightly stale profile listing is harmless.
if command -v arra-oracle-skills &>/dev/null; then
ARRA="arra-oracle-skills"
elif [ -x "$HOME/.bun/bin/arra-oracle-skills" ]; then
ARRA="$HOME/.bun/bin/arra-oracle-skills"
else
ARRA="$HOME/.bun/bin/bunx --bun github:Soul-Brews-Studio/arra-oracle-skills-cli#alpha"
fi
# $ARRA_INSTALL — anything that WRITES skills to disk. Always from GitHub.
ARRA_INSTALL="$HOME/.bun/bin/bunx --bun github:Soul-Brews-Studio/arra-oracle-skills-cli#alpha"
Why they differ. The installed binary carries its own frozen copy of every skill — the
set as of the day you installed it. Installing through it therefore writes those skills
over whatever you have now. Once the binary is older than your skills (normal after a few
weeks) every "install" is really a downgrade; a 26.5.15 binary was seen overwriting
26.7.25 skills. Reading through it costs you nothing, so keep the fast path for reads and
take the network hit only when writing.
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.
- 11d ago First seen · 513 lines · 66 tokens per session scan B 882dd840fe6f
go is a skill published in the GitHub repository Soul-Brews-Studio/arra-oracle-skills-cli (121 stars, last pushed 5d ago), licensed MIT. It adds 66 tokens to every session and 5,713 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 3 findings (reads agent configuration directories, makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…