Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Soul-Brews-Studio/arra-oracle-skills-cli/plugin install oracle-skillsWrote 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/who-are-you)<a href="https://agentmods.dev/skills/soul-brews-studio/arra-oracle-skills-cli/who-are-you"><img src="https://agentmods.dev/badge/skills/soul-brews-studio/arra-oracle-skills-cli/who-are-you/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/who-are-you"><img src="https://agentmods.dev/badge/skills/soul-brews-studio/arra-oracle-skills-cli/who-are-you.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 | $0.00093 | $0.02140 |
| Opus 5 | $0.00046 | $0.01070 |
| Sonnet 5 | $0.00019 | $0.00428 |
| Haiku 4.5 | $0.00009 | $0.00214 |
Grade A, and why
who-are-you 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 13d 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.
How it starts
The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/who-are-you - Know Ourselves
"γνῶθι σεαυτόν" (Know thyself) - Oracle at Delphi
Usage
/who-are-you # Full identity (technical + philosophy)
/who-are-you tech # Technical only (model, tokens, shell)
Step 0: Timestamp + Output Format
date "+🕐 %H:%M %Z (%A %d %B %Y)"
(Chained with Step 1 bash call below — single date emission, then the gather block.)
Output Format
Full /who-are-you Output
# /who-are-you
## Identity
**I am**: [Oracle Name if configured, else "Claude"]
**Model**: [model name] ([variant])
**Provider**: [anthropic/openai/etc]
## Shell & CLI
**CLI Tool**: [Claude Code / OpenCode / Cursor / etc.]
**Shell**: [bash/zsh] ([version])
**Terminal**: [outer terminal] → [multiplexer] ([session:window])
**Host**: [hostname] ([SSH from X.X.X.X] | [local, no SSH])
**OS**: [macOS / Linux / Windows]
## Location
**Project**: [current project name]
**Path**: [physical path from pwd -P]
**Logical**: [logical path from pwd, only show if different from physical]
## Session
**Duration**: [time since start]
**Messages**: [count user / assistant]
## Philosophy
[Include /philosophy output here]
Step 1: Gather Technical Info
Read from environment and context:
# Shell info
echo "Shell: $SHELL"
$SHELL --version 2>/dev/null | head -1
# OS info
uname -s -r
# Check for Oracle identity in CLAUDE.md or project config
if [[ -f "CLAUDE.md" ]]; then
grep -E "^(I am|Identity|Oracle):" CLAUDE.md | head -1
fi
# Get project info (both logical and physical paths for transparency)
basename "$(pwd -P)"
echo "LOGICAL=$(pwd)"
echo "PHYSICAL=$(pwd -P)"
Detect Terminal Chain
Detect the full terminal viewing chain instead of just $TERM_PROGRAM:
# Step 1: Detect outer terminal emulator (leaks through tmux via env vars)
if [ -n "$WEZTERM_EXECUTABLE" ]; then OUTER_TERM="WezTerm"
elif [ -n "$CMUX_SOCKET_PATH" ]; then OUTER_TERM="cmux (Ghostty)"
elif [ -n "$GHOSTTY_RESOURCES_DIR" ]; then OUTER_TERM="Ghostty"
elif [ -n "$ITERM_SESSION_ID" ]; then OUTER_TERM="iTerm2"
elif [ "$TERM_PROGRAM" = "tmux" ]; then OUTER_TERM="tmux (outer terminal unknown)"
else OUTER_TERM="${TERM_PROGRAM:-unknown}"
fi
echo "OUTER_TERM=$OUTER_TERM"
# Step 2: Detect SSH chain
if [ -n "$SSH_CONNECTION" ]; then
SSH_FROM=$(echo $SSH_CONNECTION | awk '{print $1}')
echo "SSH: from $SSH_FROM → $(hostname)"
else
echo "SSH: none (local)"
fi
# Step 3: Detect tmux session context
if [ -n "$TMUX" ]; then
tmux display-message -p 'TMUX_SESSION=#{session_name}:#{window_name}'
fi
# Step 4: Full workspace view (WezTerm only)
if [ -n "$WEZTERM_EXECUTABLE" ]; then
# Env socket may be stale if WezTerm restarted — find current
WEZTERM_PID=$(pgrep -x wezterm-gui 2>/dev/null | head -1)
if [ -n "$WEZTERM_PID" ]; then
CURRENT_SOCK="$HOME/.local/share/wezterm/gui-sock-$WEZTERM_PID"
if [ -S "$CURRENT_SOCK" ]; then
WEZTERM_UNIX_SOCKET=$CURRENT_SOCK wezterm cli list 2>/dev/null | head -20
fi
fi
fi
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.
- 13d ago First seen · 303 lines · 93 tokens per session scan A 2f501990efd5
who-are-you is a skill published in the GitHub repository Soul-Brews-Studio/arra-oracle-skills-cli (121 stars, last pushed 6d ago), licensed MIT. It adds 93 tokens to every session and 2,140 once invoked, about $0.0005 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
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…