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 skills/egregore-labs/egregore/tutorialnpx skills add egregore-labs/egregore --skill tutorialgit clone --depth 1 https://github.com/egregore-labs/egregoreWrote 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/egregore-labs/egregore/tutorial)<a href="https://agentmods.dev/skills/egregore-labs/egregore/tutorial"><img src="https://agentmods.dev/badge/skills/egregore-labs/egregore/tutorial.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 | $0.00045 | $0.06538 |
| Opus 5 | $0.00023 | $0.03269 |
| Sonnet 5 | $0.00009 | $0.01308 |
| Haiku 4.5 | $0.00005 | $0.00654 |
Grade A, and why
tutorial 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 4d 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 — 640 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interactive walkthrough of Egregore's core loop.
When to invoke
User says: "/tutorial", "walk me through Egregore", "show me how this works", "teach me the core loop", or is a new user ready to try the /activity → /reflect → /quest//add loop hands-on.
Not this: first-time identity/org setup → /onboarding
Arguments: $ARGUMENTS
Tagging rule (applies to ALL artifacts and quests created during the tutorial)
Every artifact and quest created during the tutorial MUST include tutorial-generated in its topics array. This tag lets /handoff, /activity, and other commands distinguish tutorial outputs from organic session work. Handoffs exclude tutorial-generated artifacts from the Session Artifacts section.
This applies to: Step 2 reflect artifacts, Step 3 quests, Step 3 source artifacts, and the Step 4 journey log.
CRITICAL: Suppress raw output. Never show raw JSON to the user. All bin/graph.sh and bin/notify.sh calls MUST capture output in a variable and only show formatted status lines.
Mode detection
MODE=$(jq -r '.mode // "connected"' egregore.json 2>/dev/null)
Local mode (mode === "local"): Skip ALL bin/graph.sh and bin/notify.sh calls — do NOT run them. Do NOT show any graph-related messaging (knowledge graph, Neo4j, nodes, relationships, edges, "linked", "synced to graph", etc.). The tutorial in local mode is markdown-only: it creates artifact files in memory/knowledge/{findings,patterns,decisions}/, quest files in memory/quests/, and a journey log. No graph queries, no node creation, no edge counts. When the tutorial talks about what the team knows, refer to "shared memory" or "memory files" — not "the knowledge graph." Show (feature of hosted version — coming soon) where a graph-only capability is referenced.
Step 0: State Check
Read .egregore-state.json. Extract usage_type, tutorial_complete, and any existing tutorial state (domain, stage, team_or_solo).
Check for harvest data from /onboarding: If the state file contains onboarding.harvest_rounds, the user already answered identity and connection questions during onboarding. Extract and map this data so Step 1 can skip redundant questions:
rolefrom harvest round 1 → can informdomain(e.g.,engineering→software,research→research)focusfrom harvest round 2 → contextual seed for Step 2 questions
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.
- 4d ago First seen · 640 lines · 45 tokens per session scan A 58b17bf68d64
tutorial is a skill published in the GitHub repository egregore-labs/egregore (280 stars, last pushed 8d ago), licensed MIT. It adds 45 tokens to every session and 6,538 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 skills, from other repositories
scaffold-exercises
Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section.
teach
Teach the user a new skill or concept, within this workspace.
ubuntu-collective-knowledge-task-designer
Design learning tasks built on Ubuntu philosophy emphasising collective knowledge-building and mutual responsibility. Use when fostering collaboration that values community over individual competition.
dispositional-knowledge-assessment-designer
Design multi-informant assessment approaches for dispositional competencies like curiosity or resilience. Use when assessing character strengths or competencies that written tests cannot capture.
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
ljg-learn
Deep concept anatomist that deconstructs any concept through 8 exploration dimensions (history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics, meta-philosophy) and compresses insights into an epiphany. Use when user asks to explain, dissect, or deeply understand a concept, term, or…