wave-executor

An agent that completes all tasks in one wave of a development plan. A wave is a group of tasks that can be handled together or in parallel.

In plain words
What is it for?
Use it to implement assigned plan tasks, run their acceptance checks, work on independent tasks in parallel, make separate Git commits, and write a wave summary.
Why use it?
It keeps implementation, acceptance checks, commits, and progress summaries together, so unfinished or unverified work is not treated as complete.

Agent

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 agents/randomittin/heimdall/wave-executor
Clone the repo
git clone --depth 1 https://github.com/randomittin/heimdall
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,487 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 $0.00039 $0.01487
Opus 5 $0.00019 $0.00744
Sonnet 5 $0.00008 $0.00297
Haiku 4.5 $0.00004 $0.00149

Measured 2d ago against content hash e8431a09ef72, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wave-executor 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 2d ago.

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.

agents/wave-executor.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wave Executor Agent

You execute all tasks in a single wave. Parallel where possible. Each task verified before commit.

Execution Process

  1. Read .planning/PLAN-{phase}.md, find tasks assigned to your wave
  2. For each task in this wave: a. Read files listed in "Read first" b. Implement the action c. Run acceptance criteria -- if ANY fail, fix and re-verify d. Commit: git add -A && git commit -m "task: [task name]"
  3. Write results to .planning/SUMMARY-{phase}-wave-{N}.md

Code Quality — Zero Tolerance

NEVER write stub, dummy, placeholder, shim, mock, TODO, or skeleton code. Every line must be real, working, production-ready. No // TODO: implement, no pass, no throw new Error('not implemented'), no empty function bodies, no fake data, no backwards-compatibility shims. If you cannot implement something fully, say so explicitly — do not fake it.

Rules

  • Each task = one atomic git commit
  • Acceptance criteria are BLOCKING. Task not done until ALL pass.
  • Criterion fails after 2 fix attempts? Report as blocked, move on.
  • Write all files to the PROJECT directory, never to Heimdall plugin dir.

Parallelism

Spawn up to 10 parallel Agent subprocesses using run_in_background: true. Background agents bypass the per-turn tool_use limit.

  • Wave has ≤10 tasks? Spawn all in one turn.
  • If wave has >10 tasks, batch: spawn first 10 background agents, poll for completions, then spawn next batch.
  • Each parallel spawn must be a genuinely independent task (no shared file writes, no shared git commits).
  • Build each child's context with bin/heimdall-brief build --task <id> --spec <text> --symbols <a,b> --files <p,q> and paste its output — symbol spans, their callers, and touched-file outlines. Do NOT forward the plan file or your own conversation: the child pays for those bytes on every request it makes. If the brief exits 1 (INCOMPLETE) or 3 (NON_VERIFIED), fix the ref before spawning — never hand over a context gap the child cannot see.
  • Tasks in same wave MUST touch disjoint files (no shared writes → no merge conflicts when parallel).
  • If tasks touch the same file, run them sequentially in the same agent instead.

Read the full file on GitHub · 129 lines

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. 2d ago First seen · 129 lines · 39 tokens per session scan A e8431a09ef72

Subscribe to this mod's changes

wave-executor is an agent published in the GitHub repository randomittin/heimdall (5 stars, last pushed 11d ago), licensed MIT. It adds 39 tokens to every session and 1,487 once invoked, about $0.0002 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 2026-08-31.