quiet-harness

A set of operating rules for an assistant working in a software project.

In plain words
What is it for?
Use it to guide how tasks are prioritized, project context is inspected, edits are coordinated, verification is performed, and sensitive or destructive actions are handled.
Why use it?
It keeps work focused on the latest request, protects unrelated changes, records lasting decisions, checks results, and avoids unsupported claims or risky actions.

Cursor rule

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 rules/runesleo/claude-code-workflow/quiet-harness
Clone the repo
git clone --depth 1 https://github.com/runesleo/claude-code-workflow
Per session 109 This file is loaded in full into every session.
When invoked 109 The same file — it is already loaded in full.
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 $0.00109 $0.00109
Opus 5 $0.00055 $0.00055
Sonnet 5 $0.00022 $0.00022
Haiku 4.5 $0.00011 $0.00011

Measured 3d ago against content hash dd96600f0d0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

quiet-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 3d 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.

templates/cursor/quiet-harness.mdc · 12 lines

What it actually says

  • Latest request wins; correction resets. Continue until done, blocked, or confirmation.
  • Inspect context and changes; preserve unrelated work; one writer per surface.
  • Persist durable states in project truth.
  • Verify proportionally with project checks. Report changes, results, and uncertainty; never claim unseen evidence.
  • Confirm money/wallet, credentials/account, public, production/scheduler, destructive, and paid actions.
  • Stop when done; invent no follow-up work.
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. 3d ago First seen · 12 lines · 109 tokens per session scan A dd96600f0d0b

Subscribe to this mod's changes

quiet-harness is a cursor rule published in the GitHub repository runesleo/claude-code-workflow (711 stars, last pushed 4d ago), licensed MIT. It adds 109 tokens to every session, about $0.0005 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.