By jskswamy
Filter shell output noise and auto-install dependencies for the aide CLI, keeping sandbox and context management sessions clean.
Agent management — list agents, check binaries, add or remove
Config review — validate configuration, suggest hardening and optimization
Context diagnostics — explain match resolution, manage contexts and rules
Run full diagnostic across context, sandbox, secrets, and config
Environment variable management — list, set, wire from secrets
Use this skill when the user wants to review, validate, or improve their aide configuration. Triggers on: "review config", "review aide config", "is my config correct", "optimize aide", "harden sandbox", "aide validate", "check aide setup". Routes to /aide doctor for full diagnostic or /aide sandbox, /aide context for specific areas.
Use this skill when the user reports context or agent selection issues with aide. Triggers on: "wrong agent", "wrong context", "why is it using", "launched the wrong agent", "expected claude but got", "context mismatch", "aide which", "which context". Do NOT trigger for general agent setup — use setup-guide for that.
Use this skill when the user reports sandbox or permission issues with their aide-managed agent. Triggers on: "permission denied", "operation not permitted", "agent hanging", "agent stuck", "can't write to", "can't read", "sandbox blocking", "sandbox error", "seatbelt", "sandbox-exec". Do NOT trigger for general file permission issues unrelated to aide or sandboxing.
Use this skill when the user reports API authentication or missing credential issues with an aide-managed agent. Triggers on: "can't access API", "missing key", "missing API key", "authentication failed", "API error", "unauthorized", "401", "403", "invalid credentials", "no API key". Do NOT trigger for general coding authentication issues unrelated to aide context/secrets.
Use this skill when the user wants to set up or initialize aide. Triggers on: "set up aide", "configure aide", "initialize aide", "aide init", "new project aide", "get started with aide", "install aide". Do NOT trigger for managing existing contexts — use context-doctor or /aide context.
Executes bash commands
Hook triggers when Bash tool is used
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Stop babysitting your agent.
One command. Any agent. Sandboxed, reproducible, zero decision fatigue.
You planned the work. You know what needs to happen. But instead of letting your agent execute, you're stuck evaluating every file read, every shell command, every network call. That's not autonomy — that's babysitting with extra steps.
aide fixes three things:
Without aide, you either skip all permissions and hope for the best:
claude --dangerously-skip-permissions # what could go wrong?
Or you click "allow" on every. single. action. File read? Allow. Shell command? Allow. Network call? Allow. Two hundred times a session.
With aide, the agent runs inside OS-native guardrails — no config, no prompts:
aide # agent launches sandboxed automatically
🔧 aide · work (claude)
📁 github.com/acme/api
🛡 sandbox: network outbound, code-only
Code-only mode. Your agent can read your code, run tests, hit the network — but it physically cannot touch your SSH keys, cloud credentials, or browser data. 10 guards active by default, zero configuration.
Ready to deploy? Tell aide what you're doing:
aide --with docker # build and push images
aide --with docker k8s # deploy to your cluster
aide --with docker k8s gcp # debug cloud infra too
🔧 aide · work (claude)
📁 github.com/acme/api
🛡 sandbox: network outbound
✓ docker ~/.docker/config.json
✓ k8s ~/.kube/config (KUBECONFIG)
✓ gcp ~/.config/gcloud
⚠ credentials exposed: GOOGLE_APPLICATION_CREDENTIALS
Each capability unlocks exactly what the agent needs — nothing more. Docker gets registry creds. Kubernetes gets kubeconfig. GCP gets gcloud auth. Everything else stays locked.
Protect what matters:
aide cap never-allow ~/.kube/prod-config
aide cap never-allow --env PRODUCTION_DB_PASSWORD
Now no capability — not even k8s — can ever read your production kubeconfig. The agent sees your dev and staging clusters but production is a hard wall:
🔧 aide · work (claude)
🛡 sandbox: network outbound
✓ k8s ~/.kube/dev-config, ~/.kube/staging-config
✗ denied ~/.kube/prod-config (never-allow)
Make it permanent for a project:
# .aide.yaml in your repo root
capabilities: [docker, k8s, gcp]
No flags needed next time — aide picks up the capabilities from your config.
The first time aide encounters a .aide.yaml, it shows the contents and asks you to trust it:
aide trust # approve the project config
aide deny # block it permanently
Create your own:
aide cap create k8s-dev --extends k8s --deny ~/.kube/prod-config
aide --with k8s-dev docker # dev clusters only, production blocked
19 built-in capabilities: aws, gcp, azure, docker, k8s, helm, terraform, vault, ssh, npm, go, rust, python, ruby, java, github, gpg, and more. Or define your own.
Without aide, every agent is its own world:
claude # Anthropic API key
CLAUDE_CODE_USE_BEDROCK=1 AWS_PROFILE=work claude # or Bedrock?
codex --provider anthropic # different CLI entirely
aider --model claude-3.5-sonnet # yet another interface
Different CLIs. Different config formats. Different env vars. Switch agents, rewire everything.
With aide, you configure once and forget:
cd ~/work/project && aide # Claude with work Bedrock credentials
cd ~/oss/repo && aide # Aider with personal Anthropic key
cd ~/scratch && aide # auto-detects agent on PATH, zero config
Same command everywhere. aide resolves the right agent, credentials, and sandbox from your project directory.
Without aide:
# The classic footgun
echo 'ANTHROPIC_API_KEY=sk-ant-...' >> .env
git add -A && git commit -m "update config" # oops
API keys in .env files. Wrapper scripts with hardcoded tokens. A new machine means an hour of setup.
With aide, secrets are encrypted at rest and never exist as plaintext on disk:
aide secrets create personal --age-key age1abc... # encrypted with your key
Config and encrypted secrets live in git. Clone your config on a new machine and you're done. No shared secrets, no plaintext on disk.
# Install latest release (macOS)
curl -sSfL https://raw.githubusercontent.com/jskswamy/aide/main/install.sh | sh
# Install to a specific directory
curl -sSfL https://raw.githubusercontent.com/jskswamy/aide/main/install.sh | INSTALL_DIR=/usr/local/bin sudo sh
# Install a specific version
curl -sSfL https://raw.githubusercontent.com/jskswamy/aide/main/install.sh | VERSION=v0.1.0 sh
Guardrails for Claude - IDE refactoring handoff, commit message validation, extensible to security, cost, and testing patterns
Generate visual sketch notes in Excalidraw format from conversations, code architecture, or custom content
Quick, low-friction capture of notes, tasks, ideas, session summaries, tech radar blips, and Feynman-style teaching notes with Obsidian-style auto-linking
Generate beautiful PDF/HTML shareable notes using Typst with 7 professional templates, infographics, and modern typography
Initialize and manage Nix flake development environments with auto-detection and security tooling
npx claudepluginhub jskswamy/aide --plugin aideComplete AI coding workflow system. Self-correcting memory + persistent FTS5-indexed research wikis + auto-research loop + multi-LLM council on a single SQLite store. 33 skills, 8 agents, 22 commands, 37 hook scripts across 24 events. Cross-agent via SkillKit.
Open-source, local-first Claude Code plugin for token reduction, context compression, and cost optimization using hybrid RAG retrieval (BM25 + vector search), reranking, AST-aware chunking, and compact context packets.
MCP server that saves 98% of your context window with session continuity. Sandboxed code execution in 11 languages, FTS5 knowledge base with BM25 ranking, and automatic state restore across compactions.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).