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/joris887/exosuit/discovernpx skills add joris887/exosuit --skill discovergit clone --depth 1 https://github.com/joris887/exosuitWrote 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/joris887/exosuit/discover)<a href="https://agentmods.dev/skills/joris887/exosuit/discover"><img src="https://agentmods.dev/badge/skills/joris887/exosuit/discover.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 5.1 | $0.00028 | $0.07208 |
| Opus 5 | $0.00014 | $0.03604 |
| Sonnet 5 | $0.00006 | $0.01442 |
| Haiku 4.5 | $0.00003 | $0.00721 |
Grade A, and why
discover 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 5d 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 — 647 lines — stays where its author put it; the contents beside it link to each section on GitHub.
discover
Deep guided elicitation for: $ARGUMENTS
Read references/question-scaffolding.md — these 8 rules apply to EVERY question you ask. Read @.claude/prompts/interactive-ux.md for the shared interactive UX protocol (AskUserQuestion format, progress tracking, confirmation gates).
Process Flow (authoritative)
START → Phase 1: Classification (archetype + scale + 5 universal questions)
→ Mode Selection:
→ [QUICK: --quick flag OR Quick Build scale]
→ 3-5 essential questions → 1 research → auto-pick tech → minimal backlog → DONE
→ [GUIDED: Standard scale — DEFAULT]
→ Phase 2 → 3 → 4 → 5 → 6 → 7 → DONE
→ [PLATFORM: --platform flag OR Platform scale]
→ All GUIDED phases + stakeholder/compliance/multi-user/ADRs → DONE
→ [PIONEERING: --pioneer flag OR Pioneering scale]
→ Core identity → deep research → spike planning → spike backlog → DONE
Phase 1: Classification
Show the opening progress bar:
---
**Discover** | Phase 1 of 7: Classification
[>....................] 0 of ~22 decisions
Coming up: What kind of project is this, and how big?
---
Let's start by understanding what kind of project this is. I'll ask 4-5 quick
questions to classify your idea — this takes about 2 minutes.
1A. Archetype Selection (recognition-based — use AskUserQuestion)
Analyze the user's idea description from Phase 0. Identify the top 3 matching archetypes. Present via AskUserQuestion:
header: "Project type"
question: "Based on your description, your project seems closest to one of these.
Which fits best? Select 'Other' to see all 11 options or describe
something different."
options:
- label: "[Best match] (Recommended)"
description: "[one-sentence archetype description]. Like [3 examples]."
- label: "[Second match]"
description: "[one-sentence description]. Like [3 examples]."
- label: "[Third match]"
description: "[one-sentence description]. Like [3 examples]."
What ships with it
21 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/assumption-register.md 1.1 KB
- assets/decision-log.md 1003 B
- assets/phase-walkthrough.md 1.0 KB
- references/archetypes/automation.md 2.1 KB
- references/archetypes/creative-platform.md 2.0 KB
- references/archetypes/dashboard.md 2.0 KB
- references/archetypes/devtool.md 2.0 KB
- references/archetypes/educational.md 1.9 KB
- references/archetypes/experiential.md 2.1 KB
- references/archetypes/marketplace.md 2.3 KB
- references/archetypes/personal.md 1.8 KB
- references/archetypes/uncategorized.md 2.2 KB
- references/archetypes/utility.md 2.0 KB
- references/archetypes/viral.md 2.1 KB
- references/dimension-sweep.md 6.6 KB
- references/engineering-by-archetype.md 5.1 KB
- references/external-dependencies.md 6.5 KB
- references/phase-transition-template.md 4.3 KB
- references/question-scaffolding.md 3.7 KB
- references/research-protocols.md 4.7 KB
- references/scale-guide.md 5.2 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.
- 5d ago First seen · 647 lines · 28 tokens per session scan A b4285923306c
discover is a skill published in the GitHub repository joris887/exosuit (4 stars, last pushed 16d ago), licensed MIT. It adds 28 tokens to every session and 7,208 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 skills, from other repositories
issue-triage
Issue triage: audit open issues, categorize, detect duplicates, cross-ref PRs, risk assessment, post comments. Args: "all" for deep analysis of all, issue numbers to focus (e.g. "42 57"), "en"/"fr" for language, no arg = audit only in French.
build-teaql-app
Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…
moai-workflow-worktree
Git worktree management for parallel SPEC development with isolated workspaces, automatic branch registration, and seamless MoAI-ADK integration. Use when setting up parallel development environments.
moai-kanban-foreman
One unattended kanban foreman iteration: watch the backlog queue, dispatch the next operator-picked card to an isolated worker, collect completion evidence on read (not on claims), and report. This is the body the project's loop.md driver invokes each iteration of a bare /loop; it can also be invoked directly to test…
moai-workflow-thinking
Sequential Thinking MCP for structured step-by-step analysis via --deepthink flag. Separate from UltraThink which is Claude's native extended reasoning mode. Use for multi-step analysis or architecture decisions.
moai-domain-uiux
UI/UX design systems specialist covering accessibility, icons, theming, design tokens, and user experience patterns. Use when working on design systems, WCAG compliance, ARIA patterns, or dark mode theming.