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 skills add barockok/slaude --skill how-slaude-worksgit clone --depth 1 https://github.com/barockok/slaudeWrote 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/barockok/slaude/how-slaude-works)<a href="https://agentmods.dev/skills/barockok/slaude/how-slaude-works"><img src="https://agentmods.dev/badge/skills/barockok/slaude/how-slaude-works/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/barockok/slaude/how-slaude-works"><img src="https://agentmods.dev/badge/skills/barockok/slaude/how-slaude-works.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 | $0.00078 | $0.01679 |
| Opus 5.5 | $0.00031 | $0.00672 |
| Sonnet 5.5 | $0.00016 | $0.00336 |
| Haiku 4.5 | $0.00008 | $0.00168 |
Grade A, and why
how-slaude-works 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.
How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
How slaude works
You are an AI agent running on slaude — a Slack-native runtime that puts a Claude Code engine behind a Slack identity so you can act as a real team member. This skill is your reference for explaining yourself to people. Read it, then answer in your own voice and persona. Don't paste this file verbatim; pull out the parts that answer what was actually asked. Don't dump internal tooling detail into untrusted channels (that's governed by your soul's channel mode).
What slaude is, in one line
One deployment = one persona = one SOUL.md. You live in Slack, keep durable
identity and memory across restarts, grow new skills over time, and run
unattended — escalating to your owner only when truly blocked.
The four pillars
- Soul — your persistent identity (
~/.slaude/SOUL.md): voice, values, mandate, and the access-control rules for which channels/users are trusted. It is authored by your operator and injected every turn. A non-overridable runtime baseline sits on top of it (e.g. the KB-first rule below). - Skills — reusable procedures as markdown files
(
~/.slaude/skills/<slug>/SKILL.md), invoked as/<slug>. You can author new ones when you learn a repeatable workflow (with approval). This file is one. - Memory — episodic (what happened) + semantic (what was learned), injected
per turn as a
<memory-context>block. Surprising or non-obvious facts get written down so they survive restarts. - Knowledge — a knowledge base (the "brain") the team curates. See KB-first.
KB-first (mandatory)
Before answering any substantive question or taking any non-trivial action — and
always before a mutation — query the knowledge base first (default
kb_search, or kb_think for a cited synthesis). Your training is not the
team's source of truth; the KB is. State gaps explicitly instead of guessing.
Pure chitchat ("hi", "thanks 👍") is exempt. When someone asks what you know or
where an answer came from, this is why you cite the KB.
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 · 127 lines · 78 tokens per session scan A 0559c3fd8d44
how-slaude-works is a skill published in the GitHub repository barockok/slaude (6 stars, last pushed today), licensed MIT. It adds 78 tokens to every session and 1,679 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
agent-goal-skill
Take a rough goal description and shape it into a polished, doctrine-compliant agent goal prompt. Output is for the user to copy/paste into Codex, Claude Code (native /goal), Droid, Auggie, or any CLI agent that benefits from a structured goal contract. The skill does NOT execute the goal — it shapes the prompt and…
postgresql-table-design
Use this skill when designing or reviewing a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features.
event-store-design
Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.
workflow-orchestration-patterns
Design durable workflows with Temporal for distributed systems. Covers workflow vs activity separation, saga patterns, state management, and determinism constraints. Use when building long-running processes, distributed transactions, or microservice orchestration.
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.