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 joris887/exosuit --skill uninstallgit 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/uninstall)<a href="https://agentmods.dev/skills/joris887/exosuit/uninstall"><img src="https://agentmods.dev/badge/skills/joris887/exosuit/uninstall.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 | $0.00020 | $0.01455 |
| Opus 5 | $0.00010 | $0.00727 |
| Sonnet 5 | $0.00004 | $0.00291 |
| Haiku 4.5 | $0.00002 | $0.00145 |
Grade F, and why
uninstall scanned grade F with 4 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 6d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/joris887/exosuit/main/install.sh | bash Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls -d .claude/skills/ .claude/hooks/ .claude/rules/ .claude/agents/ .claude/prompts/ .claude/commands/ .claude/output-styles/ .claude/scripts/ 2>/dev/null Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf .claude/skills/ .claude/hooks/ .claude/rules/ .claude/agents/ .claude/prompts/ .claude/commands/ .claude/output-styles/ .claude/scripts/ Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/joris887/exosuit/main/install.sh | bash How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
uninstall
Remove the Exosuit framework from this project.
Phase 0: Confirm Intent
Ask the user to confirm using AskUserQuestion:
- "Full removal" — description: "Remove all framework files (.claude/, framework docs, scripts). Keep source code, tests, and project docs untouched."
- "Keep documentation" — description: "Remove framework machinery (.claude/) but keep generated docs (ARCHITECTURE.md, CODING_STANDARDS.md, GROUND_RULES.md, etc.)"
- "Cancel" — description: "Don't remove anything"
Phase 1: Inventory
Before removing, inventory what exists:
Framework Files (will be removed)
# Core framework
echo "=== Core Framework ==="
ls -d .claude/skills/ .claude/hooks/ .claude/rules/ .claude/agents/ .claude/prompts/ .claude/commands/ .claude/output-styles/ .claude/scripts/ 2>/dev/null
# Settings and config
echo "=== Settings ==="
ls .claude/settings.json .claude/settings.local.json.template .claude/keybindings.json.template 2>/dev/null
# Framework scripts
echo "=== Scripts ==="
ls scripts/pm/*.sh 2>/dev/null
# Framework root files
echo "=== Root Files ==="
ls install.sh AGENTS.md llms.txt CLAUDE.local.md.template 2>/dev/null
Project-Specific Content (will be PRESERVED)
echo "=== Preserved ==="
ls docs/architecture/ docs/reference/ docs/context/ docs/testing/ docs/sessions/ docs/adr/ docs/progress.md docs/technical-debt.md CLAUDE.md 2>/dev/null
Technology-Specific Skills (ask user)
# Skills generated by /skill-create for the project's stack
echo "=== Technology Skills (project-specific) ==="
for skill_dir in .claude/skills/*/; do
skill_name=$(basename "$skill_dir")
# Check if it's a framework skill or a tech skill
case "$skill_name" in
bootstrap|sprint-start|story-cycle|sprint-end|continue|handoff|brainstorm|ideate|research|skill-create|code-quality|test-validator|security-audit|architecture-check|manual-test|testing-cycle|UAT-cycle|claude-sense-check|debug-session|fix-issue|undo-work|commit|parallel-work|weekly-maintenance|retrospective|backlog-review|doctor|framework-upgrade|pr-status|skill-eval|refine-loop|optimize|quickstart|help-me|dashboard|custom-hooks|uninstall|performance-check)
;; # Framework skill — will be removed
*)
echo " $skill_name (technology-specific)"
;;
esac
done
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.
- 6d ago First seen · 162 lines · 20 tokens per session scan F b12bd964a116
uninstall is a skill published in the GitHub repository joris887/exosuit (4 stars, last pushed 17d ago), licensed MIT. It adds 20 tokens to every session and 1,455 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it F with 4 findings (downloads and executes remote code, enumerates other installed skills, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
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.
linkedin-post
You take a YouTube video transcript and produce a single LinkedIn post draft.