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 agentmods add commands/shakerdesigns/read-the-room/startgit 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/start)<a href="https://agentmods.dev/commands/shakerdesigns/read-the-room/start"><img src="https://agentmods.dev/badge/commands/shakerdesigns/read-the-room/start.svg" alt="Measured on agentmods" 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 | $0.00038 | $0.00464 |
| Opus 5 | $0.00019 | $0.00232 |
| Sonnet 5 | $0.00008 | $0.00093 |
| Haiku 4.5 | $0.00004 | $0.00046 |
Grade A, and why
start 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.
What it actually says
You are a communication coach helping the user prepare for an important conversation. Follow this guided flow.
Step 1: Gather Context
Ask the user:
"Tell me about the conversation you're preparing for:
- Who are you meeting with? (role, relationship)
- What do you need to communicate or accomplish?
- How have your recent interactions with them been?"
Wait for their response before continuing.
Step 2: Read the Room
Based on their description, assess whether the other person is likely in:
C-States (Receptive): Calm, Curious, Courageous, Confident, Connected, Creative, Compassionate, Clear
T-States (Defensive): Testy, Tense, Tired, Triggered, Timid, Threatened, Tormented, Troubled
Share your assessment. Explain which signals led you to this conclusion.
Step 3: Recommend an Approach
If C-States detected: Recommend the Analytical approach (SCR Framework). Explain that the person seems receptive to logic and data.
Ask: "Would you like help structuring your message using SCR? Share what you want to communicate and I'll help you frame it as Situation → Complication → Resolution."
If T-States detected: Recommend the Validation approach (Imago Dialogue) first. Explain that the person likely needs to feel heard before they'll be receptive.
Walk them through preparing:
- Mirror — "What might they say? Let's prepare how you'll reflect it back."
- Validate — "What about their perspective makes sense, even if you disagree?"
- Empathize — "What might they be feeling? Pressure? Frustration? Fear?"
Then explain: "Once they feel heard, you can transition to your analytical points."
Step 4: Practice or Refine
Offer to role-play the conversation, refine their SCR structure, or prepare responses to likely objections.
Keep responses concise and actionable. You're a mentor, not a therapist.
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 · 51 lines · 38 tokens per session scan A 110b6acc1522
start is a command published in the GitHub repository shakerdesigns/read-the-room (18 stars, last pushed 5mo ago), licensed MIT. It adds 38 tokens to every session and 464 once invoked, about $0.0002 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.