Search everything...

Stats

Actions

Available In

evo-talos Devkit

Name: evo-talos Devkit
Author: evolplus

By evolplus

Orchestrate the full SDLC within Claude Code using role-based agents for requirements, architecture, task planning, implementation, testing, and deployment, with automated governance gates, commit discipline, and local environment provisioning.

npx claudepluginhub evolplus/talos --plugin talos

Popularity

Stars

Top 25%

Med: 0·Avg: 281

Installs

Med: 0·Avg: 1

What's Inside

Slash Commands2

Sdlc Init

/sdlc-init

Initialize the current project with the Evo Talos SDLC AGENTS.md contract by default, or Claude Code project files when --target claude is supplied.

Setup (do this once, before the loop)

/sdlc-loop

Run the SDLC orchestration loop — auto-dispatch eligible tasks until a gate, blocker, circuit-breaker, or completion. Starts the loop once instead of repeatedly prompting "continue".

Agents28

agent-generator

/agent-generator

Meta-agent that generates and refreshes role-specific sub-agent files in .claude/agents/. Two modes: `default` (post-sign-off, full SRS-derived specialization for every SDLC role) and `bootstrap` (pre-sign-off, skeleton-only for a single requested role — used to break the BA / SA-extract / SA-adequacy chicken-and-egg). See _meta/agent-generator.md § Dispatch Modes.

code-reviewer

/code-reviewer

Non-SDLC review agent (Path B3). Lens-driven cold code review (security / performance / consistency / correctness). Produces docs/code-reviews/<scope-slug>.md. Never modifies code — findings re-enter via BA (non-trivial) or land as qa/infra-track tasks (trivial).

Solution Architect

/sa

You are the Solution Architect sub-agent. You translate product requirements or brownfield evidence into implementation-ready architecture.

codebase-archaeologist

/codebase-archaeologist

Non-SDLC reverse-engineering agent (Path B5, brownfield onboarding Stage 1). Read-only sweep of existing codebase + git history + deployed env + non-kit docs. Produces docs/archaeology-reports/<topic-slug>.md — informational input for SA `extract` + BA Mode E. Not a kit-canonical artifact.

debugger

/debugger

Non-SDLC diagnostic agent (Path B2). Read-only triage / root-cause analysis of bugs, regressions, production incidents. Produces docs/debug-reports/<incident-slug>.md. May propose master-plan tasks for trivial fixes (single-line, single-file, no behavior change beyond fix) per the trivial-fix exemption.

Skills45

ba-mode-augment

/ba-mode-augment

BA Phase 1.D ingestion mode (augment-existing) — the steady-state mode for most post-initial-ingest dispatches. Load when Shape Detection selects Mode D. Captures operator-supplied new requirements VERBATIM to docs/requirements/conversational-additions/ BEFORE any synthesis, per CLAUDE.md §10.

ba-mode-external-source

/ba-mode-external-source

BA Phase 1.C ingestion mode (ingest-from-external-source). Load when Shape Detection selects Mode C: SRS content lives in an external system (Confluence/Notion/Jira/SharePoint) reached via MCP. Materializes external content into the kit's three-file shape, records provenance, and handles the re-ingestion path.

ba-mode-multi-doc

/ba-mode-multi-doc

BA Phase 1.B ingestion mode (ingest-from-multi-doc). Load when Shape Detection selects Mode B: docs/SRS.md plus some/all per-US and per-FR files already exist but the index-to-file pairing has orphans. Validates each per-file artifact and flags gaps for the common pipeline.

ba-mode-requirements-folder

/ba-mode-requirements-folder

BA Phase 1.F ingestion mode (ingest-from-requirements-folder) — greenfield with fragmented upstream. Load when Shape Detection selects Mode F: no SRS yet, but docs/requirements/ holds requirement fragments (md/txt/html, or docx/pdf when those skills are active). Synthesizes a kit-shape SRS from the fragments with full Synthesized-From provenance.

ba-mode-reverse-engineer

/ba-mode-reverse-engineer

BA Phase 1.E ingestion mode (reverse-engineer-from-code) — brownfield onboarding Stage 3. Load when Shape Detection selects Mode E: no SRS yet, but docs/archaeology-reports/ and an extracted docs/architecture.md exist. Derives a kit-shape SRS from code + archaeology + architecture, then halts for the mandatory Stage 4 human-confirmation gate.

Hooks1

Event Hooks

Bash

File writes

24 hooks across 4 events

Stats

Version0.2

ReleasedJun 20, 2026

LanguageJavaScript

Stars8

MaintenanceExcellent

LicenseApache-2.0

Last CommitJun 20, 2026

AddedJun 17, 2026

Actions

View on GitHub View README Plugin Marketplace JSON

Own this plugin?

Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).

Available In

evo-talos8

Safety Signals

Caution

Executes bash commands

Hook triggers when Bash tool is used

Modifies files

Hook triggers on file write and edit operations

README

evo-talos Devkit Plugin

End-to-end SDLC orchestration kit for Claude Code and Codex. The plugin packages role agents, slash commands, on-demand skills, operating rules, safer settings, runtime hooks, and Codex-compatible skill metadata so a project can move from requirements to architecture, design, implementation, deployment, and QA with explicit artifacts and gates.

For a visual walkthrough, open the static guide:

Usage guide - workflow diagram, entry tracks, design flows, FE/BE framework tracks, QA/deployment tracks, and artifact ownership.

Token Usage Notice

This kit can consume a large amount of tokens. That is intentional: evo-talos is designed for SDLC governance, artifact traceability, role separation, validation gates, QA evidence, and keeping a project on track rather than for minimal one-shot code edits.

Use it when the cost of coordination mistakes, missing requirements, weak QA, or uncontrolled implementation drift is higher than the cost of extra model usage. For small throwaway changes, a direct Claude Code prompt may be more efficient.

What This Plugin Does

evo-talos turns Claude Code or Codex from a single coding assistant into a structured SDLC coordinator. It gives the assistant a project-local operating model with:

Role-based agents for BA, SA, TL, UI/UX Designer, BE Dev, FE Dev, DevOps, QA-Author, QA-Exec, and support roles.
Claude Code slash commands and Codex command-shim skills for project setup and autonomous SDLC progression.
Skills that load detailed instructions only when needed, reducing runtime token overhead.
Hooks that guard privacy, plan consistency, SRS sign-off, source-code writes, Docker scope, QA evidence, and dependency safety.
Artifact ownership rules so each role writes only the documents it owns.
Worktree isolation and plan-update.json protocols for parallel execution.

When To Use It

Use this kit when you want Claude Code to help run a disciplined software delivery flow rather than just edit files. It supports:

Greenfield projects starting from a PRD or raw requirement document.
Projects with an existing SRS and per-story/per-FR documentation.
Requirements stored across a folder of source documents.
External-source ingestion from systems such as Confluence, Notion, Jira, or SharePoint when connectors are available.
Brownfield onboarding where code exists but trustworthy SRS/architecture docs do not.
Figma-first product work where design content needs to feed the SRS.
Iterative scope changes after sign-off.

Main Workflow

Install or enable the plugin in Claude Code or Codex.
Initialize the target project:
- Claude Code: run /sdlc-init.
- Codex: prompt Run sdlc-init.
Provide the starting source: PRD, SRS, requirements folder, external source, Figma URL, or existing codebase.
Start the loop:
- Claude Code: run /sdlc-loop.
- Codex: prompt Start the SDLC loop or Run sdlc-loop.
Answer blocking questions only when the kit halts for required human context or approval.
Review generated artifacts, deployment reports, and QA reports before accepting completion.

The high-level flow is:

Initialize:
  Claude Code: /sdlc-init
  Codex: Run sdlc-init
Start or continue:
  Claude Code: /sdlc-loop
  Codex: Start the SDLC loop
  -> BA requirements ingestion and SRS sign-off
  -> UI/UX design extraction, mapping, creation, import, revision, or incorporation
  -> SA architecture, ADRs, integration adequacy, and instrumentation contracts
  -> TL task planning
  -> BE/FE implementation
  -> DevOps local deployment
  -> QA-Exec runtime verification
  -> iteration or done

Commands And Codex Skill Entrypoints

Claude Code loads command files from commands/, so it exposes /sdlc-init and /sdlc-loop as slash commands.

Codex plugins currently use skills and starter prompts rather than plugin slash-command files. For Codex, the plugin provides equivalent command-shim skills:

sdlc-init - invoke with Run sdlc-init, Run sdlc-init --dry-run, or Initialize this project with Evo Talos.
sdlc-loop - invoke with Run sdlc-loop, Start project, or Continue the SDLC loop.

`/sdlc-init`

Initializes the current project for the kit.

/sdlc-init

Optional flags:

/sdlc-init --target codex
/sdlc-init --target claude
/sdlc-init --target both
/sdlc-init --dry-run
/sdlc-init --force-hooks
/sdlc-init --skip-agents
/sdlc-init --skip-settings
/sdlc-init --skip-hooks

What it does:

View full README on GitHub

evo-talos Devkit

Popularity

What's Inside

Confidence

README

evo-talos Devkit Plugin

Token Usage Notice

What This Plugin Does

When To Use It

Main Workflow

Commands And Codex Skill Entrypoints

`/sdlc-init`

Similar Plugins

llm-council-plugin

caveman

ui-design

self-improving-agent

evo-talos Devkit Plugin

Token Usage Notice

What This Plugin Does

When To Use It

Main Workflow

Commands And Codex Skill Entrypoints

`/sdlc-init`

Popularity

Health & Quality

Similar Plugins

llm-council-plugin

caveman

ui-design

self-improving-agent

claude-mem

nanobanana