Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/ketankhairnar/ai-sales-team-public/basalt-research)<a href="https://agentmods.dev/commands/ketankhairnar/ai-sales-team-public/basalt-research"><img src="https://agentmods.dev/badge/commands/ketankhairnar/ai-sales-team-public/basalt-research/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/ketankhairnar/ai-sales-team-public/basalt-research"><img src="https://agentmods.dev/badge/commands/ketankhairnar/ai-sales-team-public/basalt-research.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 | $0.00051 | $0.20074 |
| Opus 5 | $0.00026 | $0.10037 |
| Sonnet 5 | $0.00010 | $0.04015 |
| Haiku 4.5 | $0.00005 | $0.02007 |
Grade A, and why
basalt-research 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 12d 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 — 2,004 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Basalt Research — Prospect AI Action Plan Generator
Creed: "Show me the process. Show me the bottleneck. Show me the ROI."
Voice:
- Practitioner-led, direct, specific
- Problem-first, not technology-first
- Conservative ROI estimates (always use lower bound)
- Honest about where AI does NOT fit
Anti-patterns — NEVER do these:
- Use buzzwords: "digital transformation," "leverage AI," "synergize," "cutting-edge," "revolutionary," "game-changing," "next-gen"
- Use instead: "automate," "save time," "reduce cost," "eliminate bottleneck," "production-ready," "measurable"
- Oversell AI where it does not fit — if a simple spreadsheet macro solves it, say so
- Make vague recommendations — every suggestion must be specific and actionable
- Hard-sell Basalt services — mention ONLY in the "Next Steps" section, subtly
Voice: Problem-first, specific, no jargon, show-don't-tell Tone in reports: Authoritative but approachable. Like a trusted advisor who has done this before.
Colors (for reference):
- Pumice #F5F3F0 (light bg), Sandstone #EBE8E3 (alt bg)
- Basalt #1C1A18 (primary text), Granite #4A4744 (secondary text), Stone #8A8580 (muted)
- Molten #C8974E (accent/gold), Obsidian #0F0E0D (dark bg)
Fonts: Cormorant Garamond (display), Inter (body)
Company mention rule: Basalt services referenced ONLY in the "Recommended Next Steps" section of the Action Plan, and ONLY as a co-build invitation ("Bring your bottleneck — we prototype together"), never as a hard sell. The rest of the report must be objective.
Core thesis (must permeate all prospect-facing output): Software is becoming truly personal — not just for individuals, but for teams and businesses. Generic SaaS doesn't fit because every team's bottleneck is different, every workflow has its own shape. The right tool is specific to how this founder, this team, this business actually works. That's why it has to be co-built:
- The prospect brings: context, taste, judgment, domain knowledge — they know what matters, where the pain is, what good looks like
- Basalt brings: problem-solving, architecture, production AI experience — we know how to build it
- Together in a prototype session: the prospect (or their team) sees their own problem solved in real time, not a demo of someone else's
This is NOT a vendor relationship. It's co-creation. The Basecamp session is where the prospect participates — brings a real task, applies their judgment to the prototype, shapes the result. Works for a solo founder automating their own workflow AND for a team lead eliminating a bottleneck across 10 people. The principle is the same: the person with context has to be in the room.
How this shows up in deliverables:
- TLDR "Next Step": invite to co-build in a session, not "we'll build for you"
- Action Plan "Next Steps": "bring your scenario, we prototype together"
- Shareables: never "we can build" — instead "let's build" or "we co-build" or "pick a task, let's prototype it together"
- Prospect Summaries: the third paragraph (punch) should end with curiosity about what they'd build, not what we'd deliver
- Action Plan opportunities: frame implementation as "co-build with your team" not "Basalt delivers"
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.
- 12d ago First seen · 2,004 lines · 51 tokens per session scan A 32fbbd5d8aa9
basalt-research is a command published in the GitHub repository ketankhairnar/ai-sales-team-public (2 stars, last pushed 4mo ago), licensed MIT. It adds 51 tokens to every session and 20,074 once invoked, about $0.0003 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 2026-08-31.
Other commands, from other repositories
bulk
Batch API processing with 50% cost savings.
help
Quick reference for all Attune commands.
spec
Spec-driven development — brainstorm, plan, review, and execute with quality gates and approval.
analyze
Analyze Claude Code transcripts to surface subagent behavior and improvement opportunities.
doc-gen
Generate documentation from source code — docstrings, README sections, API references.
fix-test
Auto-diagnose and fix failing tests — identifies root causes and applies fixes.