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/lassare-hq/agent-configsWrote 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/lassare-hq/agent-configs/lassare-slack)<a href="https://agentmods.dev/commands/lassare-hq/agent-configs/lassare-slack"><img src="https://agentmods.dev/badge/commands/lassare-hq/agent-configs/lassare-slack/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/lassare-hq/agent-configs/lassare-slack"><img src="https://agentmods.dev/badge/commands/lassare-hq/agent-configs/lassare-slack.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 | $0.00011 | $0.00469 |
| Opus 5 | $0.00005 | $0.00234 |
| Sonnet 5 | $0.00002 | $0.00094 |
| Haiku 4.5 | $0.00001 | $0.00047 |
Grade A, and why
lassare-slack 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 8d 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
Lassare Slack Mode
⚠️ FIRST: Execute this script using the Bash tool (MANDATORY, do NOT skip)
.claude/scripts/lassare-slack.sh
You MUST run the script above using the Bash tool BEFORE doing anything else. This persists the mode to disk.
⚠️ STRICT ADHERENCE REQUIRED
When in Slack mode, you MUST use mcp__lassare__ask for ALL communication:
✅ ALWAYS use Slack for:
- ANY question, clarification, or confirmation needed
- Task completion notifications (brief recap + "What's next?")
- Before making assumptions about unclear requirements
- Significant decisions (architecture, approach, scope)
- When you're unsure about anything
❌ NEVER do these in Slack mode:
- Use
AskUserQuestiontool (inline questions) - Respond with inline text after receiving a Slack reply
- Assume the answer without asking
- Skip notification when completing significant work
- Wait until you're blocked - ask proactively
🔄 IMPORTANT: Keep the conversation in Slack
When user replies via Slack, you MUST respond back via mcp__lassare__ask - never switch to inline text. The user is on their phone, keep the conversation there.
Format
- Keep question short (<100 chars) - this is the Slack message title
- Put ALL details in
contextparameter - In
context, use real line breaks for readability — NEVER use literal\ncharacters - User responds from phone, keep it scannable
Examples
Task completion:
question: "Admin portal changes done. What's next?"
context: "Completed:
- Plan filter
- Clickable companies
- User list fix
Ready to commit."
Clarification:
question: "Should activity log show user email or ID?"
context: "Currently shows obfuscated email.
Could show user_id instead for better privacy."
Before assuming:
question: "No tests exist for this. Should I add them?"
context: "Adding plan filter to companies list.
No existing test coverage for filters."
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.
- 8d ago First seen · 70 lines · 11 tokens per session scan A f1dc6f89d2f9
lassare-slack is a command published in the GitHub repository lassare-hq/agent-configs (5 stars, last pushed 6mo ago), licensed MIT. It adds 11 tokens to every session and 469 once invoked, about $0.0001 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
init-workspace-flow-questions
Phase 8 Questions of init-workspace-flow.
sdd-apply
Implement SDD tasks — writes code following specs and design.
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
init
Initialize configurations for Supabase local development.
ijfw-audit
Run the IJFW audit gate for the current workflow phase. Usage: /ijfw-audit [phase name].
api-aqa-flow-execution-and-report-analysis
Phase 6 Execution & Report Analysis of api-aqa-flow (USER INTERACTION REQUIRED).