run

A command that explores a project and its context library, then saves the important findings in one intake document. It records the request, involved repositories, customers, success measure, and unresolved questions.

In plain words
What is it for?
Use it as the first step when starting a feature workflow and preparing context for a product requirements document.
Why use it?
It prevents later workflow stages from repeatedly searching the same project or stopping to ask for information that can be gathered from the repository. Unresolved items are recorded clearly so work can continue.

Command for Claude Code

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/pierry/harness-kit/run
Clone the repo
git clone --depth 1 https://github.com/Pierry/harness-kit

Made for: Claude Code.

Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 292 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 $0.00028 $0.00292
Opus 5 $0.00014 $0.00146
Sonnet 5 $0.00006 $0.00058
Haiku 4.5 $0.00003 $0.00029

Measured yesterday against content hash c87ff1097ac6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

run 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/commands/intake/run.md · 30 lines

What it actually says

Run intake. Record intent so the status bar tracks it:

.claude/scripts/pipeline.py intent intake

Dispatch the intake subagent via the Task tool (subagent_type: intake), so the heavy repo exploration runs in an isolated context and only the distilled intake.md returns. Pass the raw idea (and any repo path the user named) as the prompt.

The subagent explores the repo + context-library, computes feature_id, attaches it with pipeline.py set-feature, and writes .claude/runtime/outputs/intake/{feature_id}.md with a structured frontmatter (squad, repos, customers, metric, unknowns) and an <!-- approved: --> marker.

When the subagent returns, relay its report and surface unknowns:

intake saved at {path}.
  feature_id: {feature_id}
  unknowns:   {n} — {short list or "none"}
  next:       /product-manager:prd

If unknowns is non-empty, name them so the human can fill any that matter before the PRD gate. Do not block: the pipeline proceeds with the markers in place.

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 · 30 lines · 28 tokens per session scan A c87ff1097ac6

Subscribe to this mod's changes

run is a command published in the GitHub repository Pierry/harness-kit (3 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 292 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 2026-08-31.