dependency-checker

Estrelas11

Forks3

Atualizado29 de julho de 2026 às 18:52

Verify the framework's toolchain (git, bash, jq, gh, yq, PowerShell 7+, Node.js/npx, uv/uvx, shellcheck, Claude Code CLI) is installed and working — use when setting up the framework, after system updates, or when hooks, validators, MCP servers, or the executor agents fail with "command not found".

Instalação

Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.

Fonte

tomas-rampas

tomas-rampas/agentic-framework

Abrir repositório GitHub Ver repositórios do creator

Download

Ocupações relacionadasSOC

Baseado na classificação ocupacional SOC

Desenvolvedores de softwareInformática e Matemática·SOC 15-1252

SKILL.md

readonly

Mais deste repositório

mesmo repositório

hook-config-generator

tomas-rampas/agentic-framework

Guide for adding a new real Claude Code hook to this framework as a .ps1/.sh pair (registration in hooks/hooks.json as a shell-form chain, tests in both suites, validation) — use when asked to create, generate, or extend a hook or quality gate.

2026-07-2911

agent-routing-advisor

tomas-rampas/agentic-framework

Recommends which framework agent (or multi-agent workflow) should handle a task; use when the user asks which agent to use, how to delegate a piece of work, or how to sequence agents for a multi-domain task.

2026-07-2911

agent-debugger

tomas-rampas/agentic-framework

Diagnose and fix agent routing, loading, and configuration issues by inspecting agents/*.md frontmatter, the claude.json registry, hook registration, and validator output — use when an agent is "not found", tasks route to the wrong specialist, models mismatch, hooks do not fire, or validate-consistency.sh fails.

2026-07-2911

git-workflow-assistant

tomas-rampas/agentic-framework

Git branching, commit, PR, conflict-resolution, and release guidance integrated with the framework's peer-review final gate — use when planning branches, writing commit messages, preparing or opening PRs, resolving merge conflicts, cutting releases, or when the Stop gate blocks a session over unreviewed committed work.

2026-07-2611

code-scoring-loop

tomas-rampas/agentic-framework

Iteratively improve a code change by having the matching specialist agent score the diff 0-100 against an explicit rubric, rewriting the weakest parts, and repeating until the score plateaus. Use after the quality bar is green (build/lint/format/tests clean) but before the review gates — e.g. polishing an implementation or refactor, or when asked to "clean up" code without concrete criteria. Code-side sibling of self-scoring-loop.

2026-07-2611

self-scoring-loop

tomas-rampas/agentic-framework

Iteratively improve a non-code deliverable (spec, plan, document, design) by writing an explicit rubric, scoring the work 0-100 against it, rewriting the weakest parts, and repeating until the score plateaus. Use when a deliverable has a quality bar but no test suite — e.g. before handing over a spec, proposal, architecture doc, or report.

2026-07-2611

name	dependency-checker
description	Verify the framework's toolchain (git, bash, jq, gh, yq, PowerShell 7+, Node.js/npx, uv/uvx, shellcheck, Claude Code CLI) is installed and working — use when setting up the framework, after system updates, or when hooks, validators, MCP servers, or the executor agents fail with "command not found".

Dependency Checker

Verify that every external tool this framework actually depends on is installed, on PATH, and at a workable version. Run the probes below, report a concise status table, and give platform-specific remediation for anything missing. Never invent results — run each probe and report exactly what it returns.

When to Use

First-time setup of the Claude Code environment (before installing the agentic-framework plugin)
After OS or package-manager updates
When a hook, validator script, or MCP server fails with "command not found" or a spawn error
When onboarding a new machine to the framework
When /agentic-framework:validate-hooks or /agentic-framework:analyze-framework report tool-related failures

What Needs What

Tool	Required by
git	Hard requirement; the Stop-gate hook's branch-vs-base checks; all repo workflows
bash (Git Bash on Windows)	`scripts/validate-consistency.sh`, `scripts/validate-hooks.sh`, `scripts/validate-framework.sh`, `scripts/generate-docs.sh`, `tests/consistency.test.sh`
jq	The bash validators (`validate-consistency.sh` aborts without it); parsing the registry (`claude.json`) and config files
gh (GitHub CLI)	The command-line executor agents (bash-expert, powershell-expert): PR/issue/run queries, log grinding, `gh api` reads; must be authenticated
yq (mikefarah v4)	The executor agents: YAML processing and agent-frontmatter extraction (`yq --front-matter=extract`)
PowerShell 7+ (`pwsh`)	Windows: installer scripts require pwsh 7, and the hook chain falls back to it (hooks/dispatch.sh runs the POSIX .sh directly when jq is on PATH in Git Bash; .ps1 via pwsh otherwise). Linux/macOS: optional — hooks run as POSIX shell; pwsh only needed for the optional .ps1 test suite (`tests/hooks.test.ps1`).
Node.js + npx	The `filesystem`, `context7`, and `sequential-thinking` MCP servers (launched via `npx -y`) — only needed if the optional agentic-framework-mcp plugin is installed
uv (`uvx`)	The `serena` and `fetch` MCP servers — only needed if the optional agentic-framework-mcp plugin is installed
Claude Code CLI	Host runtime that loads the agentic-framework plugin and executes hooks
shellcheck (optional)	Linting `scripts/*.sh`; nice-to-have, nothing hard-fails without it

Probes

Run each probe and classify the result as OK (with version), MISSING, or WRONG VERSION. On Windows, run PowerShell probes in pwsh and shell probes in Git Bash.

git

Probe: git --version
Pass: any modern version (2.30+). Also confirm the repo resolves: git -C <repo> rev-parse --is-inside-work-tree prints true.

bash

Probe: bash --version (first line). On Windows, confirm Git Bash specifically: bash -c 'echo ok' must print ok; Git for Windows installs it at C:\Program Files\Git\bin\bash.exe.
Pass: bash 4+ (Git Bash ships 5.x). WSL bash also works for the validators, but paths must then be WSL-style.

jq

Probe: jq --version
Pass: 1.6 or newer. Sanity check: jq -e '.sub_agents | length > 0' claude.json from the repo root exits 0.

gh (GitHub CLI)

Probe: gh --version, then gh auth status (exit 0 = authenticated; never pass --show-token).
Pass: 2.0+. Unauthenticated gh means the executor agents' GitHub queries all fail — remediate with gh auth login.

yq

Probe: yq --version
Pass: must report https://github.com/mikefarah/yq v4+. The Python yq (a jq wrapper) has incompatible syntax and does NOT satisfy this dependency.

PowerShell 7+

Probe: pwsh -NoProfile -Command '$PSVersionTable.PSVersion.ToString()'
Pass: 7.0 or newer. powershell.exe (Windows PowerShell 5.1) is NOT sufficient — the hook scripts refuse to run under it.
Windows: REQUIRED — the installer and the hook fallback need pwsh 7+ (dispatch.sh routes to the .ps1 when jq is missing from Git Bash, and the || arm runs it when sh is unavailable; with jq present, hooks run as POSIX .sh and skip pwsh entirely).
Linux/macOS: OPTIONAL — hooks run as POSIX shell natively; pwsh is only needed if you want to run the .ps1 test suite for verification (for example, in CI when both interpreters are available for equivalence testing).

Node.js and npx

Probes: node --version and npx --version
Pass: Node 18+ (LTS recommended). npx must resolve — the MCP servers are launched as npx -y <package>.

uv / uvx

Probe: uvx --version (or uv --version)
Pass: any recent release. Without it the serena MCP server silently fails to start.

Claude Code CLI

Probe: claude --version
Pass: any current release. If the optional agentic-framework-mcp plugin is installed, claude mcp list should show filesystem, context7, serena, sequential-thinking, and fetch.

shellcheck (optional)

Probe: shellcheck --version
If missing, mark OPTIONAL-MISSING, not a failure.

Functional Smoke Checks

Version probes prove installation, not integration. When the user is troubleshooting (not just installing), also run:

pwsh -NoProfile -File tests/hooks.test.ps1 — exercises the .ps1 hook implementations end to end (needs pwsh 7+ and git). Windows: required check. Linux/macOS: optional verification.
bash tests/hooks.test.sh — exercises the .sh hook implementations (needs bash and git). Linux/macOS: verifies POSIX hooks work. Windows: optional if Git Bash is available.
bash scripts/validate-consistency.sh — runs the full consistency battery (needs bash and jq); it validates the registry (claude.json), agent frontmatter parity, and hook pair parity against hooks/hooks.json.
bash scripts/validate-hooks.sh — focused hook pair-parity and dispatch check.

If a smoke check fails while all version probes pass, the problem is configuration (PATH visible to Claude Code's hook shell, plugin installation state), not a missing tool — verify the agentic-framework plugin is installed and active: /plugin list should show it, and the session may need restarting for hooks to load.

Remediation by Platform

Windows

git: winget install Git.Git (includes Git Bash)
jq: winget install jqlang.jq
gh: winget install GitHub.cli, then gh auth login
yq: winget install MikeFarah.yq
PowerShell 7: winget install Microsoft.PowerShell
Node.js: winget install OpenJS.NodeJS.LTS
uv: winget install astral-sh.uv (or irm https://astral.sh/uv/install.ps1 | iex)
shellcheck: winget install koalaman.shellcheck
Claude Code: npm install -g @anthropic-ai/claude-code or the native installer
After installing, restart the terminal (and Claude Code) so PATH changes are picked up. Verify the tool is visible from BOTH pwsh and Git Bash — hooks run under pwsh, validators under bash.

macOS

brew install git jq gh yq node uv shellcheck
brew install --cask powershell (provides pwsh)
Claude Code: npm install -g @anthropic-ai/claude-code or the native installer

Linux (Debian/Ubuntu)

sudo apt-get install -y git jq shellcheck gh (gh may need the GitHub CLI apt repo); yq: download the mikefarah binary from GitHub releases (the apt yq is the incompatible Python wrapper)
Node.js: distro package or NodeSource setup script for a current LTS
PowerShell 7: Microsoft package repository (packages.microsoft.com), then sudo apt-get install -y powershell
uv: curl -LsSf https://astral.sh/uv/install.sh | sh
Claude Code: npm install -g @anthropic-ai/claude-code or the native installer

Reporting

Present results as a single table: Tool | Status | Version found | Needed by | Fix (only for failures). Then a one-line verdict:

All required tools OK → framework is fully operational; install the agentic-framework plugin if not already done.
Any of git / bash / jq / pwsh missing → validators or hooks WILL fail; list the exact install command for the user's platform.
node/npx or uvx missing → core framework works, but the optional agentic-framework-mcp plugin's MCP servers will not start; this is non-blocking if the user doesn't need those servers.
gh or yq missing (or gh unauthenticated, or yq is the Python wrapper) → the command-line executor agents degrade: GitHub queries and YAML processing fail; give the platform install command.
Only shellcheck missing → note it as optional and move on.

Do not fabricate percentages, scores, or tool inventories beyond the table above, and do not install anything without the user asking — report and recommend.