vibecosystem
Profile-based Claude runtime with 138 agents, 296 skills, 74 hooks in the catalog; memory and orchestration are opt-in
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Badge for your README
Markdown
[](/listings/vibeeval-vibecosystem)HTML
<a href="/listings/vibeeval-vibecosystem"><img src="/api/listings/vibeeval-vibecosystem/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
Use a source checkout to try these changes. When reviewing a PR, check out its head branch before installing; cloning uses `main` by default:
git clone https://github.com/vibeeval/vibecosystem.git cd vibecosystem ./install.sh --profile core --dry-run ./install.sh --profile core
The installer uses the prebuilt hooks in `hooks/dist/`; a normal installation does not compile TypeScript or install the hook development dependencies. Node.js 18+ and Bash are required. Development checks use Node.js 22.
For the published npm version (currently 3.5.0):
npx vibecosystem init
The remote installer fetches `main` (this source tree). Review the script before running it:
curl -fsSL https://raw.githubusercontent.com/vibeeval/vibecosystem/main/install-remote.sh -o install-remote.sh bash install-remote.sh --profile core
Restart Claude Code after changing its hook registrations. Inspect the installed state with:
vibeco effective-config vibeco doctor vibeco stats
`vibeco effective-config` shows which profile is active and how many hooks are registered and compiled.
The source installer creates `~/.local/bin/vibeco` unless an unmanaged launcher already exists there. Add `~/.local/bin` to `PATH` if your shell cannot find it. You can also run the source CLI with `node tools/vibeco/vibeco.mjs`.
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
plugin.json · Manifest · 21 lines
- {
- "name": "vibecosystem",
- "description": "Profile-based Claude runtime with 138 agents, 296 skills, 74 hooks in the catalog; memory and orchestration are opt-in",
- "version": "3.5.1",
- "author": {
- "name": "vibeeval",
- "url": "https://github.com/vibeeval"
- },
- "repository": "https://github.com/vibeeval/vibecosystem",
- "license": "MIT",
- "keywords": [
- "claude-code",
- "agents",
- "skills",
- "hooks",
- "ai-team",
- "self-learning",
- "code-review",
- "tdd"
- ]
- }
README.md · README · 189 lines
- <div align="center">
- # vibecosystem
- **A focused runtime for Claude Code. A bounded worker for Codex.**
- [](LICENSE)
- **Catalog (in repo):** [](#catalog) [](#catalog) [](#catalog) [](#catalog)
- **Default core:** [](#catalog)
- [](https://github.com/vibeeval/vibecosystem/actions/workflows/validate.yml)
- [Türkçe](#turkce) · [Español](docs/README_ES.md) · [Français](docs/README_FR.md) · [Deutsch](docs/README_DE.md) · [Português](docs/README_PT.md) · [Italiano](docs/README_IT.md) · [Nederlands](docs/README_NL.md) · [中文](docs/README_ZH.md) · [日本語](docs/README_JA.md) · [한국어](docs/README_KO.md) · [العربية](docs/README_AR.md) · [हिन्दी](docs/README_HI.md) · [Русский](docs/README_RU.md)
- 
- </div>
- vibecosystem packages agents, skills and hooks for software work. The default `core` profile installs a selected set for investigation, implementation, review and verification. Memory, learning and orchestration have explicit profiles; `full` installs all 138 agents, 296 skills and 20 rules plus 53 of the 74 hooks.
- **3.5.1 is the current npm release.** See [CHANGELOG.md](CHANGELOG.md) and the [upgrade guide](UPGRADING.md).
- ## Quick start
- Use a source checkout to try these changes. When reviewing a PR, check out its head branch before installing; cloning uses `main` by default:
- ```bash
- git clone https://github.com/vibeeval/vibecosystem.git
- cd vibecosystem
- ./install.sh --profile core --dry-run
- ./install.sh --profile core
- ```
- The installer uses the prebuilt hooks in `hooks/dist/`; a normal installation does not compile TypeScript or install the hook development dependencies. Node.js 18+ and Bash are required. Development checks use Node.js 22.
- For the published npm version (currently 3.5.0):
- ```bash
- npx vibecosystem init
- ```
- The remote installer fetches `main` (this source tree). Review the script before running it:
- ```bash
- curl -fsSL https://raw.githubusercontent.com/vibeeval/vibecosystem/main/install-remote.sh -o install-remote.sh
- bash install-remote.sh --profile core
- ```
- Restart Claude Code after changing its hook registrations. Inspect the installed state with:
- ```bash
- vibeco effective-config
- vibeco doctor
- vibeco stats
- ```
- `vibeco effective-config` shows which profile is active and how many hooks are registered and compiled.
- The source installer creates `~/.local/bin/vibeco` unless an unmanaged launcher already exists there. Add `~/.local/bin` to `PATH` if your shell cannot find it. You can also run the source CLI with `node tools/vibeco/vibeco.mjs`.
- ## Profiles
- Profiles select installed components and registered hook commands. Catalog size does not describe how much prompt content is loaded into each request.
- | Profile | Purpose |
- | --- | --- |
- | `core` | Selected implementation, investigation and verification tools; default |
- | `dashboard` | Core plus opt-in local activity monitoring |
- | `quality` | Core plus focused edit, compiler and security checks |
- | `context` | Core plus targeted code context retrieval |
- | `memory` | Core plus persistent recall and learning |
- | `orchestration` | Core plus explicit multi-agent workflows |
- | `full` | All 138 agents, 296 skills and 20 rules; 53 of the 74 hooks |
- `minimal` and `smart` alias `core`; `all` aliases `full`. Legacy `frontend`, `backend`, `fullstack` and `devops` profiles retain domain allowlists with core hooks. Read the exact selection in [profiles/runtime-manifest.json](profiles/runtime-manifest.json), or use `vibeco effective-config` after installation.
- ```bash
- vibeco profile quality # core plus focused edit, compiler and security checks
- vibeco profile core # default selected set
- vibeco profile memory # core plus persistent recall and learning
- vibeco profile full # all agents, skills and rules; 53 of 74 hooks
- ```
- Profile changes reconcile installer-owned files and hook registrations. Modified or unmanaged files require review; the installer preserves ownership boundaries and creates backups before replacements. See [UPGRADING.md](UPGRADING.md).
- ## Token and runtime efficiency
- The default profile avoids installing the complete agent and skill catalog. Context-producing hooks use character limits: **4,000 per event and 12,000 per session** for lean profiles; **8,000/50,000** for `full`. These are limits on participating hook context, not limits on total model input, output, reasoning, tool results or billing.
- Token cost depends on the selected model, task, retrieved content and retries. Character counts and `estimated_tokens` are estimates; provider-reported usage is recorded separately when present. This project does not promise a fixed percentage or multiplier of token savings. Reproducible measurements belong with their fixtures and commands in [the verification record](docs/verification.md).
- The core skill entrypoint payload is smaller after focused rewrites: see the [reproducible byte comparison](docs/verification.md#core-skill-entrypoint-payload). Skills load on demand, so this is an available instruction size measurement, not a whole-session token claim.
- For routine work, stay on `core`, inspect relevant files, use one bounded implementation path and run the checks required for the change. Select `context`, `memory` or `orchestration` when the task benefits from them. Installing `full` does not automatically launch an agent swarm.
- ## How the runtime fits together
- ```mermaid
- flowchart LR
- P[Selected profile] --> I[Installer]
- I --> C[Selected agents and skills]
- I --> H[Registered Claude hooks]
- E[Claude lifecycle event] --> H
- H --> B[Bounded optional context]
- B --> W[Claude session]
- C --> W
- W --> V[Implementation and verification]
- ```
- Hooks run in response to host lifecycle events. They can inspect tool input, return a permission decision or provide context. They do not guarantee that a suggested agent or workflow will execute. Agent and skill files are instructions consumed by the host model.
- The optional memory pipeline captures and consolidates patterns under the user's Claude directory. Its thresholds are heuristics, not proof that a learned rule is correct. Review learned material before relying on it in sensitive work.
- ## Catalog
- | Path | Catalog (in repo) | Default core |
- | --- | --- | --- |
- | `agents/` | 138 Markdown agent definitions | 12 |
- | `skills/` | 296 top-level skill directories; some contain nested skills | 32 |
- | `hooks/src/` | 74 TypeScript entry points, including utilities and CLIs | 6 |
- | `rules/` | 20 rule documents; the lean profiles do not install the full rule set | - |
- The `full` profile installs 138 agents, 296 skills, 20 rules and 53 of the 74 hooks.
- Source entry points, unique hook names and registered commands are different counts. [hooks/hooks.json](hooks/hooks.json) is the registration source. Some files are command-line utilities or are not registered by default. Use `vibeco list agents --search security` to browse the installed catalog.
- ## Codex and other adapters
- | Host | Setup | Scope |
- | --- | --- | --- |
- | Claude Code | `./install.sh --profile core` | Selected agents, skills, hooks and rules |
- | Codex | `./install-codex.sh --profile core --install-luna-worker` | Selected skills and an optional bounded `luna_worker` |
- | Cursor | `./install-cursor.sh /path/to/project` | Project instructions, MDC rules and skills |
- | Other compatible hosts | Manual | Skill content; check the host's format and discovery rules |
- The Codex worker contract is [`.codex/agents/luna-worker.toml`](.codex/agents/luna-worker.toml): `gpt-5.6-luna` with `max` reasoning. The project config stays model-neutral. Claude-only `opus`/`sonnet` metadata is not applied by the Codex installer. Model availability and custom-agent support depend on the host and account. See [docs/codex-setup.md](docs/codex-setup.md).
- ## Optional integrations and data
- Core installation does not provision external services. Some optional hooks and skills need tools that are not bundled:
- - Code context and Python diagnostics use a compatible TLDR daemon; unavailable diagnostics can return no findings.
- - Memory graph features need a Node-compatible `better-sqlite3` installed in `~/.claude/hooks/`; a missing or incompatible module is reported and that graph operation skips. Other recall workflows reference Python/`uv` scripts and may need a configured database.
- - The `dashboard` profile adds one emitter to core (7 unique hook entry points across 8 registrations). It records agent starts on PreToolUse and structural tool completion events on PostToolUse; `full` includes it too. The dashboard uses the local `ws` package. Install it with `npm ci --ignore-scripts --prefix ~/.claude/tools/dashboard`, as described in [its setup guide](tools/dashboard/README.md).
- - Compiler assistance may contact a configured LM Studio endpoint. Braintrust extraction requires `VIBECO_BRAINTRUST_ANALYSIS=1`, a key and its script. GitHub-mutating hooks require `VIBECO_GITHUB_AUTOMATION=1`. MCP, search and provider skills may contact their configured services.
- Local state can contain code excerpts, prompts, tool output, errors and learned rules under `~/.claude/`. The core product is local; integrations may send data to the services you configure. Review the enabled profile, credentials and endpoint settings. The credential hook is a best-effort guard and does not replace host permissions or an operating-system sandbox. See [SECURITY.md](SECURITY.md).
- ## Development
- ```bash
- cd hooks
- npm ci
- npm run check
- npm run build
- npm test
- ```
- Keep `hooks/dist/` synchronized with source. Installer tests use temporary home directories; do not use a personal installation as a fixture. See [CONTRIBUTING.md](CONTRIBUTING.md), [ARCHITECTURE.md](ARCHITECTURE.md) and [docs/verification.md](docs/verification.md).
- ## Visuals
- The current [eight-second GIF](assets/runtime-demo.gif) is a locally rendered product diagram, not a screen recording or benchmark. Its [editable source](assets/runtime-demo-source/README.md) freezes data from the runtime manifest. The [static diagram](assets/runtime-overview.svg) describes profile selection and runtime boundaries. Earlier terminal GIFs remain in `assets/` as historical material; they depict legacy workflows and are not evidence that every feature runs in the default profile. See [assets/README.md](assets/README.md) for sources and reproduction requirements.
- <a name="turkce"></a>
- ## Türkçe
- vibecosystem, Claude Code için agent, skill ve hook'ları bir araya getirir. Varsayılan `core` profili, araştırma, geliştirme, inceleme ve doğrulama için seçilmiş bileşenleri kurar. Bellek, öğrenme ve çoklu agent akışları ayrıca seçilir; katalogdaki her şey her oturumda yüklenmez.
- ```bash
- ./install.sh --profile core --dry-run
- ./install.sh --profile core
- vibeco effective-config
- ```
- `vibeco effective-config` aktif profili ve kayıtlı hook sayısını gösterir.
- Token verimliliği için önce göreve uygun küçük profili seç. Bağlam sınırları modelin toplam token tüketimini sınırlamaz; ücret ve kullanım görevine, modele ve tekrar sayısına bağlıdır. Ölçülmemiş tasarruf oranları vaat etmiyoruz. `full` profili 138 agent, 296 skill ve 20 rule ile 74 hook'tan 53'ünü kurar; otomatik olarak bir agent ordusu başlatmaz.
- 3.5.1 şu anda npm üzerindeki güncel sürümdür. Yayınlanmış sürüm ve kurulum için İngilizce bölümü, değişiklikler için [CHANGELOG.md](CHANGELOG.md) dosyasını takip edebilirsin.
- ## Credits and license
- Built by [@vibeeval](https://x.com/vibeeval). MIT licensed. See [LICENSE](LICENSE).
- The catalog incorporates ideas credited in the individual skills and agent definitions, including work from Shannon, UI UX Pro Max, Game Studios, Skill Gateway, Pyxel, copilot-orchestra and Trail of Bits Skills. External tools and providers retain their own licenses and terms.
install-remote.sh · Bundled script · 119 lines · 1 finding marked
- #!/bin/bash
- # Usage: curl -fsSL https://raw.githubusercontent.com/vibeeval/vibecosystem/main/install-remote.sh | bash -s -- --profile core
- Note: Pipes a downloaded script directly into a shell (curl | sh / wget | bash)
- Line 2 on GitHub
- set -euo pipefail
- if [ -z "${HOME:-}" ] || [ "$HOME" = "/" ]; then
- echo "Error: HOME must be a non-root directory." >&2
- exit 1
- fi
- INSTALL_DIR="$HOME/.vibecosystem"
- REPO_URL="https://github.com/vibeeval/vibecosystem.git"
- INSTALL_ARGS=("$@")
- DRY_RUN=false
- REQUESTED_PROFILE=core
- usage() {
- echo 'Usage: install-remote.sh [--profile NAME] [--dry-run] [--force] [--prune] [--non-interactive]'
- }
- # Validate before cloning or updating. An explicit invocation never prompts.
- while [ "$#" -gt 0 ]; do
- case "$1" in
- --profile)
- [ "$#" -ge 2 ] || { echo 'Error: --profile requires a value.' >&2; exit 1; }
- REQUESTED_PROFILE="$2"
- shift
- ;;
- --profile=*) REQUESTED_PROFILE="${1#*=}" ;;
- --dry-run) DRY_RUN=true ;;
- --force|--prune|--non-interactive) ;;
- --help|-h) usage; exit 0 ;;
- *) echo "Error: unknown option: $1" >&2; exit 1 ;;
- esac
- shift
- done
- case "$REQUESTED_PROFILE" in
- core|quality|context|memory|orchestration|dashboard|full|frontend|backend|fullstack|devops|minimal|smart|all) ;;
- *) echo "Error: unknown profile: $REQUESTED_PROFILE" >&2; exit 1 ;;
- esac
- echo ''
- echo ' vibecosystem remote installer'
- echo ' =============================='
- echo ''
- command -v git >/dev/null 2>&1 || { echo 'Error: git is required.' >&2; exit 1; }
- command -v node >/dev/null 2>&1 || { echo 'Error: Node.js is required (https://nodejs.org/).' >&2; exit 1; }
- NODE_VER=$(node -v | sed 's/v//' | cut -d. -f1)
- if [ "$NODE_VER" -lt 18 ]; then
- echo "Error: Node.js >= 18 required (you have $(node -v))" >&2
- exit 1
- fi
- if [ -e "$INSTALL_DIR" ] || [ -L "$INSTALL_DIR" ]; then
- if [ -L "$INSTALL_DIR" ] || [ ! -d "$INSTALL_DIR/.git" ]; then
- echo "Error: $INSTALL_DIR is not a managed Git checkout. Preserving it." >&2
- exit 1
- fi
- origin="$(git -C "$INSTALL_DIR" remote get-url origin)"
- case "$origin" in
- "$REPO_URL"|"https://github.com/vibeeval/vibecosystem"|"git@github.com:vibeeval/vibecosystem.git") ;;
- *) echo "Error: unexpected origin at $INSTALL_DIR. Preserving it." >&2; exit 1 ;;
- esac
- if [ "$DRY_RUN" = false ]; then
- if [ -n "$(git -C "$INSTALL_DIR" status --porcelain)" ]; then
- echo "Error: $INSTALL_DIR has local changes. Commit or back them up before updating." >&2
- exit 1
- fi
- echo 'Updating existing installation...'
- if ! git -C "$INSTALL_DIR" pull --ff-only; then
- echo 'Error: update failed. Existing checkout and local files were preserved; retry when Git is ready.' >&2
- exit 1
- fi
- else
- echo 'dry-run: skipping Git updates; inspecting the existing checkout.'
- fi
- elif [ "$DRY_RUN" = true ]; then
- echo "dry-run: would clone $REPO_URL into $INSTALL_DIR and install profile $REQUESTED_PROFILE."
- echo 'No checkout or runtime files were changed.'
- exit 0
- else
- echo 'Cloning vibecosystem...'
- git clone --depth 1 "$REPO_URL" "$INSTALL_DIR"
- fi
- if [ "${#INSTALL_ARGS[@]}" -eq 0 ]; then
- echo ''
- echo 'Choose a profile:'
- echo ' 1) core Low-noise default runtime'
- echo ' 2) frontend React/Next.js focused'
- echo ' 3) backend API/DB/infra focused'
- echo ' 4) fullstack Frontend + backend'
- echo ' 5) devops CI/CD/cloud focused'
- echo ' 6) orchestration Explicit multi-agent workflows'
- echo ' 7) full Every legacy capability'
- if [ -t 0 ]; then read -r -p 'Select [1-7, default 1]: ' CHOICE; else CHOICE=1; fi
- case "$CHOICE" in
- 2) REQUESTED_PROFILE=frontend ;;
- 3) REQUESTED_PROFILE=backend ;;
- 4) REQUESTED_PROFILE=fullstack ;;
- 5) REQUESTED_PROFILE=devops ;;
- 6) REQUESTED_PROFILE=orchestration ;;
- 7) REQUESTED_PROFILE=full ;;
- *) REQUESTED_PROFILE=core ;;
- esac
- INSTALL_ARGS=(--profile "$REQUESTED_PROFILE" --prune --non-interactive)
- fi
- cd "$INSTALL_DIR"
- bash install.sh "${INSTALL_ARGS[@]}"
- if [ "$DRY_RUN" = true ]; then exit 0; fi
- echo ''
- echo 'Done! vibecosystem is ready.'
- echo ' vibeco help Show all commands'
- echo ' vibeco stats Ecosystem statistics'
- echo ' vibeco doctor Health check'
- echo ' vibeco dashboard Start optional monitoring UI'
- case ":$PATH:" in
- *":$HOME/.local/bin:"*) ;;
- *) echo 'Add ~/.local/bin to your shell PATH to run vibeco.' ;;
- esac
Version history
v3.5.111/12/2026
v3.5.011/5/2026
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.