how-slaude-works

how-slaude-works is a skill for Claude Code, Codex from barockok/slaude. It costs 78 tokens per session (1,679 once invoked), scanned A, original, MIT.

A guide to how slaude works: an AI agent that lives in Slack and uses Claude Code to act as a team member. It explains its identity, reusable procedures, memory, access rules, approvals, and scheduled work.

In plain words
What is it for?
Use it to answer questions about interacting with slaude, its commands, skills, knowledge base, memory, integrations, and scheduled jobs.
Why use it?
It helps people understand what the agent can do, how it keeps context, and when it asks its operator for permission or help.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

Good fit Use it to answer questions about interacting with slaude, its commands, skills, knowledge base, memory, integrations, and scheduled jobs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/barockok/slaude/how-slaude-works
Install

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.

Any agent
npx skills add barockok/slaude --skill how-slaude-works
Clone the repo
git clone --depth 1 https://github.com/barockok/slaude

Made for: Claude Code, Codex.

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.

agentmods badge for how-slaude-works

README.md
[![agentmods](https://agentmods.dev/badge/skills/barockok/slaude/how-slaude-works/github.svg)](https://agentmods.dev/skills/barockok/slaude/how-slaude-works)
Your own site
<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.

agentmods 80×15 button for how-slaude-works

Your own site · 80×15
<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>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,679 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00078 $0.01679
Opus 5 $0.00039 $0.00839
Sonnet 5 $0.00016 $0.00336
Haiku 4.5 $0.00008 $0.00168

Measured 10d ago against content hash 0559c3fd8d44, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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 10d 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.

skills/how-slaude-works/SKILL.md · 127 lines

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.

Read the full file on GitHub · 127 lines

Changes

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.

  1. 10d ago First seen · 127 lines · 78 tokens per session scan A 0559c3fd8d44

Subscribe to this mod's changes

how-slaude-works is a skill published in the GitHub repository barockok/slaude (5 stars, last pushed yesterday), licensed MIT. It adds 78 tokens to every session and 1,679 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

schedule

Use when scheduling recurring cron jobs or one-shot background notifications.

imMamdouhaboammar/get-fable · 13 tokens

fable-dataviz

Design and generate accessible, cohesive data visualizations, SVG charts, metric cards, and dashboard tiles with theme-adaptive styling and verified viewports. Use when creating SVG charts, rendering metrics plots, designing dashboard visuals, or visualizing performance trends — even if the user does not explicitly…

imMamdouhaboammar/get-fable · 115 tokens

fable-release

Audit and certify repository merge and release readiness against required quality gates, clean git working trees, and verified distribution artifacts. Use when preparing a release tag, validating release checklist criteria, publishing npm/PyPI packages, or certifying a branch for merge — even if the user does not…

imMamdouhaboammar/get-fable · 113 tokens

fable-security

Conduct threat modeling, vulnerability assessments, secret sanitization, and security reviews across trust boundaries, auth flows, and untrusted inputs. Use when auditing authentication/authorization logic, inspecting APIs for injection/CORS/CSRF risks, checking for hardcoded credentials, or reviewing…

imMamdouhaboammar/get-fable · 126 tokens

fable-tdd

Drive testable behavior changes and bug fixes through disciplined red-green-refactor cycles with observable regression tests. Use when implementing new features with unit/integration tests, fixing reproducible bugs, modifying business logic, or writing test-first behavior contracts — even if the user does not…

imMamdouhaboammar/get-fable · 133 tokens

memory-types-team-stores

Use when configuring shared team memory stores and knowledge graphs.

imMamdouhaboammar/get-fable · 16 tokens