harness

harness is a command for Claude Code from vinnie357/claude-skills. It costs 16 tokens per session (667 once invoked), scanned A, original, MIT.

A command that distributes several tasks across configured Altana AI agent setups and returns the results in task order. Tasks can be assigned to specific agents or spread across them automatically.

In plain words
What is it for?
Use it to run independent tasks concurrently and compare each task's agent, status, duration, and answer summary.
Why use it?
It removes the need to launch and track multiple agent tasks one by one.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions Codex.

Part of the altana plugin — 1 skill, 3 commands shipped together

Good fit Use it to run independent tasks concurrently and compare each task's agent, status, duration, and answer summary.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/vinnie357/claude-skills/harness
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.

Clone the repo
git clone --depth 1 https://github.com/vinnie357/claude-skills

Made for: Claude Code.

Or install altana, the plugin that ships this one along with the rest of its 1 skill, 3 commands.

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/vinnie357/claude-skills/harness/github.svg)](https://agentmods.dev/commands/vinnie357/claude-skills/harness)
Your own site
<a href="https://agentmods.dev/commands/vinnie357/claude-skills/harness"><img src="https://agentmods.dev/badge/commands/vinnie357/claude-skills/harness/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for harness

Your own site · 80×15
<a href="https://agentmods.dev/commands/vinnie357/claude-skills/harness"><img src="https://agentmods.dev/badge/commands/vinnie357/claude-skills/harness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 667 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00016 $0.00667
Opus 5 $0.00008 $0.00333
Sonnet 5 $0.00003 $0.00133
Haiku 4.5 $0.00002 $0.00067

Measured 5d ago against content hash 3150b5f6e4b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

harness 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.

plugins/tools/altana/commands/harness.md · 58 lines

What it actually says

Run altana harness to fan out many tasks, distributing them across configured harnesses, and present the results as a per-task table.

What it does:

  1. Parses the pipe-separated task list from the argument string.
  2. Invokes altana harness "<t1>" "<t2>" ... [--map <idx>@<harness>].
  3. Runs in the background (multiple agents run concurrently).
  4. Receives a JSON array of result objects in task order.
  5. Presents a per-task results table with harness, status, duration, and a one-line answer excerpt.

Arguments:

  • <t1> | <t2> | ... — task strings separated by | (pipe with spaces). Each becomes one element in the harness call.
  • --map idx@harness — pin a specific task index (0-based) to a named harness. Multiple --map flags are accepted. Tasks without a pin are distributed in round-robin order across all configured harnesses.

Result table format:

#  | Harness       | Status  | Duration | Answer excerpt
---|---------------|---------|----------|---------------
0  | claude-local  | done    | 9.4s     | "Hello there, fr..."
1  | codex         | done    | 4.1s     | "The fix requires..."
2  | claude-local  | crash   | 0.3s     | (see log_path)

If altana is not installed:

Install altana (see its README — it is a Zig CLI built with zig 0.16). After building, place the binary on your PATH or invoke via mise exec -- zig-out/bin/altana.

Examples:

/harness explain the delegate subcommand | explain the council subcommand | explain the harness subcommand
/harness write a docstring for parse_config | write a docstring for run_delegate | write tests for council --map 0@opus-harness
/harness "audit error handling in src/delegate.zig" | "audit error handling in src/council.zig"

Task instructions:

Parse the argument: split on | to produce the task list. Extract any --map flags from the remaining tokens.

Reconstruct the altana call: altana harness "<t1>" "<t2>" ... [--map ...]

Run in background.

Once results arrive, parse the JSON array (index corresponds to task order). Build the results table:

  • For status == "done": extract the first non-empty line of ## Answer as the excerpt.
  • For non-done statuses: show the status value and the log_path.

Present the table. For any done entries where the full response is needed, show it on request.

Load /altana:altana for protocol and config reference before running.

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 · 58 lines · 16 tokens per session scan A 3150b5f6e4b5

Subscribe to this mod's changes

harness is a command published in the GitHub repository vinnie357/claude-skills (25 stars, last pushed 3d ago), licensed MIT. It adds 16 tokens to every session and 667 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 2026-09-03.