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/bootstrapnpx skills add joris887/exosuit --skill bootstrapgit clone --depth 1 https://github.com/joris887/exosuitWhat 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 | $0.00024 | $0.11706 |
| Opus 5 | $0.00012 | $0.05853 |
| Sonnet 5 | $0.00005 | $0.02341 |
| Haiku 4.5 | $0.00002 | $0.01171 |
Grade A, and why
bootstrap 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 2d 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 — 937 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bootstrap
Setting up the Exosuit framework for this project.
Interactive UX: Read @.claude/prompts/interactive-ux.md for the shared protocol. Use AskUserQuestion for all closed-choice interactions. Show progress between major steps. Read references/question-scaffolding.md (in the discover skill) for question formatting rules — Rules 7-8 apply here too.
Process Flow (authoritative — prose below is supporting detail)
START → 0. Detect Installation Mode
→ [Plugin mode?]
→ YES: CLAUDE_PLUGIN_ROOT is set, skip .claude/ setup
→ NO: Template mode, .claude/ already in project
→ 0.5. README Management (rename framework README → FRAMEWORK_README.md)
→ 1. Detect Project State
→ [Source files exist?]
→ YES: Path A (Existing Repository)
→ A1-A3: Detect stack, commands, assess docs/coverage/architecture, measure codebase
→ A2.8: Assess type checking → A2.85: Offer quality tooling installation
→ A2.9: Stack best practices research (optional, quick depth)
→ A3.1: LLM-readiness assessment → A3.2: Technical debt assessment
→ A3.5: Generate architecture → A3.5b: Establish ground rules
→ A3.7: Detect default branch
→ A3.8: Profile detection (recommend lean/standard/strict)
→ [Lean?] → Skip A3.1-A3.5c, A5-A5.9, generate minimal docs
→ A4: Generate config + populate TESTING_STRATEGY.md
→ A4.2: Generate or update project README.md
→ A5: Run /skill-create → A5.5-A5.6: Configure hooks/rules + assess pre-commit + CI/CD
→ A5.8: Framework Readiness Report → A5.9: Generate foundation backlog
→ A6: Clean up → A7: Present summary → DONE
→ NO: Path B (New Project)
→ Read references/new-project.md for Phase 0 (Idea Capture) ONLY
→ Phase 0: Idea Capture (braindump file / inline description / fast-track)
→ After Phase 0: invoke /discover
→ [Lean profile or --quick?] → /discover --quick
→ [Otherwise] → /discover (auto-detects mode from scale)
→ /discover handles: classification, elicitation, research, vision, backlog, README
→ After /discover: continue with scaffold generation + summary → DONE
What ships with it
23 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.
- references/accuracy-safeguards.md 2.3 KB
- references/coverage-assessment.md 6.4 KB
- references/dimensions/01-problem-vision.md 1.6 KB
- references/dimensions/02-personas.md 2.7 KB
- references/dimensions/03-features-mvp.md 2.6 KB
- references/dimensions/04-ux-design.md 2.6 KB
- references/dimensions/05-frontend.md 3.1 KB
- references/dimensions/06-backend.md 3.4 KB
- references/dimensions/07-data-storage.md 3.6 KB
- references/dimensions/08-auth-security.md 3.9 KB
- references/dimensions/09-deployment.md 4.4 KB
- references/dimensions/10-business-growth.md 2.8 KB
- references/discovery-engine.md 6.6 KB
- references/foundation-backlog.md 12 KB
- references/language-standards.md 6.2 KB
- references/llm-readiness.md 5.0 KB
- references/new-project.md 6.9 KB
- references/phase-1-analysis.md 4.6 KB
- references/quality-tooling.md 8.9 KB
- references/readiness-report.md 9.8 KB
- references/stack-detection.md 5.5 KB
- references/technical-debt-assessment.md 7.9 KB
- scripts/detect-stack.sh 4.3 KB runs code
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.
- 2d ago First seen · 937 lines · 24 tokens per session scan A 14d9286f4bb7
bootstrap is a skill published in the GitHub repository joris887/exosuit (4 stars, last pushed 13d ago), licensed MIT. It adds 24 tokens to every session and 11,706 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.
ship
Build, commit, push & version bump workflow - automates the complete release cycle.
pr-review
Batch review des PRs RTK par ordre de complexité croissante (XS → S → M → L). Pour chaque PR : vérifie l'état (conflits, CLA, reviews), lit le diff complet, analyse le code en contexte, présente un résumé avec lien + taille + recommandation. Attend validation explicite avant tout merge. Poste des commentaires…
rtk-triage
Triage complet RTK : exécute issue-triage + pr-triage en parallèle, puis croise les données pour détecter doubles couvertures, trous sécurité, P0 sans PR, et conflits internes. Sauvegarde dans claudedocs/RTK-YYYY-MM-DD.md. Args: "en"/"fr" pour la langue (défaut: fr), "save" pour forcer la sauvegarde.
code-simplifier
Review RTK Rust code for idiomatic simplification. Detects over-engineering, unnecessary allocations, verbose patterns. Applies Rust idioms without changing behavior.
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…