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 edimuj/claude-rig/plugin install claude-rigWrote 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/edimuj/claude-rig/claude-rig-awareness)<a href="https://agentmods.dev/skills/edimuj/claude-rig/claude-rig-awareness"><img src="https://agentmods.dev/badge/skills/edimuj/claude-rig/claude-rig-awareness/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/edimuj/claude-rig/claude-rig-awareness"><img src="https://agentmods.dev/badge/skills/edimuj/claude-rig/claude-rig-awareness.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 | $0.00172 | $0.03582 |
| Opus 5 | $0.00086 | $0.01791 |
| Sonnet 5 | $0.00034 | $0.00716 |
| Haiku 4.5 | $0.00017 | $0.00358 |
Grade B, and why
claude-rig-awareness scanned grade B with 1 finding 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.
- **Don't write to `~/.claude/settings.json`** when a rig is active — use How it starts
The opening of the file, as written. The whole thing — 388 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude-rig Awareness
claude-rig lets users run multiple independent Claude Code configurations side by side.
Each configuration is called a rig. When a rig is active, Claude Code doesn't use
~/.claude/ directly — it uses the rig's directory instead.
How to detect the active rig
Check the CLAUDE_CONFIG_DIR environment variable. If set, you're running inside a rig.
echo $CLAUDE_CONFIG_DIR
# Example: /home/user/.claude-rig/rigs/go
If CLAUDE_CONFIG_DIR is set, that directory replaces ~/.claude/ for everything.
Settings, plugins, skills, hooks, agents, commands, CLAUDE.md — all of it lives there,
not in ~/.claude/.
If the variable is unset, there's no active rig and ~/.claude/ is the config dir as
usual.
The 3-layer config model
Configuration resolves in three layers, most specific wins:
| Layer | Location | Scope |
|---|---|---|
| Global | ~/.claude/ |
Shared across all rigs |
| Rig | ~/.claude-rig/rigs/<name>/ (CLAUDE_CONFIG_DIR) |
Per-rig override |
| Project | .claude/ in the project working dir |
Per-project override |
Rig-specific items (settings, plugins, skills, hooks, agents) are real files that override
the global ones. New rigs also isolate per-rig data by default (conversations, history,
sessions, etc.). Remaining shared items are symlinks back to ~/.claude/. Rigs can
inherit skills/agents/hooks/commands from global, and sync plugins + MCP servers.
Where things live (with active rig)
| Item | Location |
|---|---|
settings.json |
$CLAUDE_CONFIG_DIR/settings.json |
| Plugins | $CLAUDE_CONFIG_DIR/plugins/ |
| Skills | $CLAUDE_CONFIG_DIR/skills/ |
| Hooks | $CLAUDE_CONFIG_DIR/hooks/ |
| Agents | $CLAUDE_CONFIG_DIR/agents/ |
| Commands | $CLAUDE_CONFIG_DIR/commands/ |
| CLAUDE.md (rig) | $CLAUDE_CONFIG_DIR/CLAUDE.md |
| MCP servers | $CLAUDE_CONFIG_DIR/.claude.json |
| Auth files | Often symlinked — shared across rigs |
| Rig config | $CLAUDE_CONFIG_DIR/rig.json |
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 · 388 lines · 172 tokens per session scan B e907068d6446
claude-rig-awareness is a skill published in the GitHub repository edimuj/claude-rig (9 stars, last pushed 3mo ago), licensed MIT. It adds 172 tokens to every session and 3,582 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
printing-press-import
Bring a published CLI from the public library into the internal library so it's identical to a freshly-generated copy — module path reverted, manuscripts placed alongside, ready for /printing-press-polish or /printing-press-emboss. Use when the public library has a CLI you don't have locally, or to recover from a…
work
Execute an approved wish plan — orchestrate subagents per task group with fix loops, validation, and review handoff.
trace
Dispatch trace subagent to investigate unknown issues — reproduces, traces, and reports root cause for fix handoff.
preview-design
Render a real artifact through this branch's local MERIDIAN design code (not the published npm package) so the team can test the new Design Convention on the document / handoff / platform surfaces before it ships. Use for /preview-design, "preview the design convention", "render this with the new design", or Design…
sw-do
Implement a SpecWeave increment task by task through the ledger, with evidence per task and a verified close. Use for "implement this", "start working", "continue the increment", "keep going".
done
Close an increment: ledger check, specweave verify, optional review, then specweave complete. Use when all tasks are done and saying "close increment", "we are done", or "finish up".