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.
git clone --depth 1 https://github.com/shakerdesigns/read-the-roomWrote 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/commands/shakerdesigns/read-the-room/readroom)<a href="https://agentmods.dev/commands/shakerdesigns/read-the-room/readroom"><img src="https://agentmods.dev/badge/commands/shakerdesigns/read-the-room/readroom/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/commands/shakerdesigns/read-the-room/readroom"><img src="https://agentmods.dev/badge/commands/shakerdesigns/read-the-room/readroom.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 | $0.00043 | $0.00430 |
| Opus 5.5 | $0.00017 | $0.00172 |
| Sonnet 5.5 | $0.00009 | $0.00086 |
| Haiku 4.5 | $0.00004 | $0.00043 |
Grade A, and why
readroom 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 1mo 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.
What it actually says
You're helping the user assess whether someone is in a receptive state (C-states) or defensive state (T-states).
Ask: "Describe the person and your recent interactions — how have they been acting? What's their tone or body language like? Are they under any particular pressure?"
Assess Against the States
C-States (Receptive) — Ready for Analytical:
- Calm: Relaxed, measured responses
- Curious: Asking questions, leaning in
- Courageous: Open to hard truths
- Confident: Secure, not defensive
- Connected: Engaged, eye contact
- Creative: Open to new ideas
- Compassionate: Considering others
- Clear: Focused, not overwhelmed
T-States (Defensive) — Need Validation First:
- Testy: Irritable, short responses
- Tense: Tight body language, crossed arms
- Tired: Low energy, checked out
- Triggered: Emotional, raised voice
- Timid: Hesitant, avoiding eye contact
- Threatened: Defensive, protecting position
- Tormented: Visibly stressed
- Troubled: Distracted, preoccupied
Provide Your Assessment
Based on their description, identify which states are present and recommend:
Mostly C-states (4+):
"They sound receptive. Lead with your analytical points using the SCR Framework. Use /analyze if you want help structuring your message."
Any T-states (2+):
"They sound defensive. Validate them first using Imago Dialogue before presenting your case. Use /validate to prepare, then transition to /analyze once they've shifted."
Mixed signals: "It's borderline. Open with a light validation check — mirror what you're sensing — and watch their response. If they relax, go analytical. If they stay guarded, continue validating."
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.
- 1mo ago First seen · 44 lines · 43 tokens per session scan A 6e6bf8221614
readroom is a command published in the GitHub repository shakerdesigns/read-the-room (19 stars, last pushed 7mo ago), licensed MIT. It adds 43 tokens to every session and 430 once invoked, about $0.0002 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 2026-08-30.
Other commands, from other repositories
ws
Word summary — anything told at N levels, from N words down to 1 word, for anything: a topic ("russian literature"), a URL, YouTube link, file, pasted text, a question, or "this". A leading number sets N (5 by default). Shortcut for the Fabric skill's WordSummary intent.
cancel-ralph
Cancel active Ralph Loop.
engage.actions
Execute Phase 7 - Actions on Objectives and Goal Achievement.
r
Resume the last handoff and carry on with the outstanding work.
focus
You are an ADHD focus assistant. Help the user commit to ONE task and block mental distractions.
stuck
You are an ADHD-friendly unblocking assistant. Help users get unstuck when they don't know what to do.