harness:adr-fleet

harness:adr-fleet is a command for Claude Code from Intense-Visions/harness-engineering. It costs 71 tokens per session (581 once invoked), scanned A, original, MIT.

An automated workflow for turning a queue of architecture questions into proposed Architecture Decision Records, or ADRs. An ADR is a short document that records an important technical decision, its context, and its effects.

In plain words
What is it for?
Use it to select, draft, verify, and review batches of architecture decisions in isolated worktrees.
Why use it?
It organizes many pending design choices, checks the resulting documents, and leaves final acceptance to a person.

Command for Claude Code

Part of the harness-claude plugin — 85 skills, 89 commands, 17 agents, 4 hooks, 4 MCP servers shipped together

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 commands/intense-visions/harness-engineering/adr-fleet
Clone the repo
git clone --depth 1 https://github.com/Intense-Visions/harness-engineering

Made for: Claude Code.

Or install harness-claude, the plugin that ships this one along with the rest of its 85 skills, 89 commands, 17 agents, 4 hooks, 4 MCP servers.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for harness:adr-fleet

README.md
[![agentmods](https://agentmods.dev/badge/commands/intense-visions/harness-engineering/adr-fleet.svg)](https://agentmods.dev/commands/intense-visions/harness-engineering/adr-fleet)
Your own site
<a href="https://agentmods.dev/commands/intense-visions/harness-engineering/adr-fleet"><img src="https://agentmods.dev/badge/commands/intense-visions/harness-engineering/adr-fleet.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 581 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 $0.00071 $0.00581
Opus 5 $0.00036 $0.00291
Sonnet 5 $0.00014 $0.00116
Haiku 4.5 $0.00007 $0.00058

Measured 5d ago against content hash 1d64357b0ed1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

harness:adr-fleet 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 5d 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.

.claude-plugin/commands/adr-fleet.md · 41 lines

What it actually says

Phases:

  • select: Enumerate the pending-decision queue (undocumented decision points, decision-blocked work, parked forks), cross-check against existing ADRs, score and order via roadmap-pilot impact scoring, and pre-allocate a contiguous block of ADR numbers
  • confirm: Present the ranked batch in one round — already-decided points flagged for closure, each decision's key trade-off question as a fork, proposed concurrency — for a single up-front human approval
  • dispatch: Fan out worktree-isolated subagents, each running the real architecture-advisor pipeline for one decision and drafting docs/knowledge/decisions/NNNN-slug.md at status proposed, capped at the concurrency governor
  • verify: Independently confirm each returned branch has a well-formed drafted ADR (required frontmatter, unique sequential number, status proposed, Context/Decision/Consequences) and is CI-green across all target operating systems plus the project's required checks — never by subagent self-report
  • signoff: Present every verified drafted ADR in one batch pass; flip status proposed to accepted only for ADRs the human explicitly accepts; emit a one-row-per-decision summary and close already-decided candidates citing the existing ADR; never auto-accept

<execution_context> @agents/skills/claude-code/adr-fleet/SKILL.md @agents/skills/claude-code/adr-fleet/skill.yaml </execution_context>

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. 5d ago First seen · 41 lines · 71 tokens per session scan A 1d64357b0ed1

Subscribe to this mod's changes

harness:adr-fleet is a command published in the GitHub repository Intense-Visions/harness-engineering (20 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 581 once invoked, about $0.0004 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.