Borrowing it
Nothing to install: this file belongs to cardstack/boxel. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cardstack/boxel/main/.claude/skills/inspect-ai-room/SKILL.mdgit clone --depth 1 https://github.com/cardstack/boxelWrote 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/cardstack/boxel/inspect-ai-room)<a href="https://agentmods.dev/skills/cardstack/boxel/inspect-ai-room"><img src="https://agentmods.dev/badge/skills/cardstack/boxel/inspect-ai-room/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/cardstack/boxel/inspect-ai-room"><img src="https://agentmods.dev/badge/skills/cardstack/boxel/inspect-ai-room.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 | $0.00095 | $0.01444 |
| Opus 5.5 | $0.00038 | $0.00578 |
| Sonnet 5.5 | $0.00019 | $0.00289 |
| Haiku 4.5 | $0.00010 | $0.00144 |
Grade A, and why
inspect-ai-room 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 5d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inspect an AI assistant room
All inspection goes through the Matrix client API. Locally the script logs in
as aibot (password pass), which is a member of every assistant room. The
consolidated script:
node scripts/inspect-room.mjs rooms [N] # N most recent rooms, newest first
node scripts/inspect-room.mjs timeline <roomId> # decoded event timeline
node scripts/inspect-room.mjs usage <roomId> # per-turn tokens/cost + session total
node scripts/inspect-room.mjs state <roomId> # LLM model, act/ask mode, skills
node scripts/inspect-room.mjs raw <roomId> [str] # full event JSON, filtered by substring
(paths relative to this skill's base directory)
Staging / production rooms
The aibot password for deployed environments is not readable by the
boxel-claude-readonly AWS role (checked; ssm:GetParameter on
BOXEL_AIBOT_PASSWORD is denied by design). Instead the script reuses the
Matrix token that boxel-cli stores in ~/.boxel-cli/profiles.json:
node scripts/inspect-room.mjs --profile staging timeline '!abc:stack.cards'
node scripts/inspect-room.mjs --profile staging usage '!abc:stack.cards'
node scripts/inspect-room.mjs --profile @me:stack.cards rooms 10
--profile takes a profile id or a substring of its matrixUrl
(staging, boxel.ai). A substring that matches more than one profile is
rejected; pass the exact id then. Every subcommand works; rooms lists the
profile user's rooms, not all rooms. Room ids on staging end in :stack.cards;
quote them in the shell because of the !.
Limits: the profile's user must be a member of the room (the user who ran the
session — that is the normal case when the user tests on staging with the same
account boxel-cli is logged in as). If the token was revoked, boxel profile add re-authenticates. MATRIX_URL + MATRIX_TOKEN env vars are the raw
fallback for a token from elsewhere (e.g. copied from the browser's
auth localStorage entry).
Analysis procedure for a "this session is full of errors" report
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.
- 5d ago First seen · 115 lines · 95 tokens per session scan A bb2fc61bf792
inspect-ai-room is a skill published in the GitHub repository cardstack/boxel (27 stars, last pushed today), licensed MIT. It adds 95 tokens to every session and 1,444 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-21.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
ci-fixer
CI failures - read error, minimal fix, verify.