wave

A Go-based tool for running multi-step AI workflows, with each step handled in an isolated workspace by a defined persona and connected through shared outputs.

In plain words
What is it for?
Use it to configure AI agents, write pipelines, manage their workspaces and permissions, pass artifacts between steps, and run workflows from the command line.
Why use it?
It organizes complex agent work into controlled steps with permissions, time limits, and checks that each step produces what the next one needs.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/re-cinq/wave/wave
Any agent
npx skills add re-cinq/wave --skill wave
Clone the repo
git clone --depth 1 https://github.com/re-cinq/wave

Made for: Claude Code, Codex.

Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,032 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00024 $0.01032
Opus 5 $0.00012 $0.00516
Sonnet 5 $0.00005 $0.00206
Haiku 4.5 $0.00002 $0.00103

Measured yesterday against content hash 36ab9bd4e048, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wave scanned grade A with 0 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 yesterday.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/wave/SKILL.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wave — Multi-Agent Pipeline Orchestrator

Go CLI orchestrating multi-step AI workflows. Each pipeline step runs in an isolated workspace under a named persona with enforced permissions, artifact chaining, and contract validation.

Manifest (wave.yaml)

apiVersion: v1
kind: WaveManifest
metadata:
  name: my-project

adapters:
  claude:
    binary: claude
    mode: headless
    output_format: json
    project_files: [CLAUDE.md, .claude/settings.json]
    default_permissions:
      allowed_tools: [Read, Write, Edit, Bash]

personas:
  navigator:
    adapter: claude
    system_prompt_file: .wave/personas/navigator.md
    model: sonnet                        # opus | sonnet | haiku
    permissions:
      allowed_tools: [Read, Glob, Grep, "Bash(git log*)", "Bash(git status*)"]
      deny: ["Write(*)", "Edit(*)", "Bash(git commit*)", "Bash(git push*)"]

runtime:
  workspace_root: .wave/workspaces
  max_concurrent_workers: 5
  default_timeout_minutes: 30
  relay:
    token_threshold_percent: 80
    strategy: summarize_to_checkpoint
    summarizer_persona: summarizer

skill_mounts:
  - path: .wave/skills/

Pipeline (.wave/pipelines/<name>.yaml)

kind: WavePipeline
metadata:
  name: gh-pr-review
  release: true

steps:
  - id: analyze
    persona: navigator
    dependencies: []
    memory:
      strategy: fresh
      inject_artifacts:
        - step: prior-step
          artifact: artifact-name
          as: local-filename            # available at artifacts/<as>
    exec:
      type: prompt
      source: |
        Analyze the code for: {{ input }}
    output_artifacts:
      - name: analysis
        path: output/analysis.json
        type: json
    handover:
      contract:
        type: json_schema               # or: command
        schema_path: .wave/contracts/analysis.schema.json
        source: output/analysis.json
        must_pass: true
        on_failure: retry
        max_retries: 2

Built-in Personas

Persona Role
navigator Read-only codebase exploration
craftsman Code implementation & testing
implementer Full execution specialist
philosopher Architecture & specification
auditor Security review & QA
summarizer Context compaction for relay
reviewer Quality review & validation
github-commenter Post GitHub issue comments

Read the full file on GitHub · 154 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. yesterday First seen · 154 lines · 24 tokens per session scan A 36ab9bd4e048

Subscribe to this mod's changes

wave is a skill published in the GitHub repository re-cinq/wave (20 stars, last pushed 4mo ago), licensed MIT. It adds 24 tokens to every session and 1,032 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

coordinate-agents

Route Codex-native multi-agent orchestration in a Git repository through a local-first, recoverable Agent Bus. Use for role-based planning, task execution, review, recovery, adapters, and human-gated release workflows. The plugin supports Codex CLI, Google Antigravity CLI, Claude, and other configured coding agents.…

hogancv/coordinate-agents · 87 tokens

coordinate-task

Run a Coordinate Agents Task from requirement clarification through planning, implementation, review, and the human release gate. Hide Agent Bus transport details behind the durable Task API.

hogancv/coordinate-agents · 35 tokens

coordinate-recover

Diagnose and safely resume Coordinate Agents Tasks after executable failure, non-zero exit, timeout, stale claim, processing message, or Implementer ERROR. Recovery is explicit and never an automatic retry loop.

hogancv/coordinate-agents · 43 tokens

coordinate-setup

Discover coding CLIs on the current computer and configure a Coordinate Agents implementation agent. Use for setup, executable checks, registered agents, user-level configuration, and project-over-user precedence.

hogancv/coordinate-agents · 40 tokens

coordinate-review

Review a Coordinate Agents implementation as the Codex Reviewer. Verify the real commit, diff, tests, validation evidence, and specification without modifying the Implementer's product code.

hogancv/coordinate-agents · 36 tokens

api-contracts

Enforce API contract governance, strict backward compatibility, schema validation, and standardized RFC 7807 error responses.

rafaelghif/antigravity-agents · 26 tokens