A procedure for adding or changing checks in the project's scanner, including where checks belong, how they read code, and which tests and guides must change.

Use it when creating or modifying checks in the scanner's dimensions, such as context, skills, hooks, sensors, CI, or hygiene.

It keeps new checks testable and keeps their IDs, evidence, scores, documentation, and expected maturity levels consistent.

checks — Cursor rule for Cursor by paladini/harness-score

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/paladini/harness-score

Made for: Cursor.

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.

README.md

[![agentmods](https://agentmods.dev/badge/rules/paladini/harness-score/checks/github.svg)](https://agentmods.dev/rules/paladini/harness-score/checks)

Your own site

<a href="https://agentmods.dev/rules/paladini/harness-score/checks"><img src="https://agentmods.dev/badge/rules/paladini/harness-score/checks/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.

Your own site · 80×15

<a href="https://agentmods.dev/rules/paladini/harness-score/checks"><img src="https://agentmods.dev/badge/rules/paladini/harness-score/checks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Nothing until a file matches its globs; then the whole rule loads.

When invoked 404 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00404
Opus 5.5	$0.00000	$0.00162
Sonnet 5.5	$0.00000	$0.00081
Haiku 4.5	$0.00000	$0.00040

Measured 1mo ago against content hash b8c0a0ea6b67, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

checks 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 1mo 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.

.cursor/rules/checks.mdc · 31 lines

What it actually says

Adding a check:

Pick the dimension file (context.ts, skills.ts, hooks.ts, sensors.ts, ci.ts, hygiene.ts) and the next free ID in that family's sequence (e.g. SNS-06).
A check reads ONLY through ScanContext (has / read / matching) — never fs directly, so tests can fake it.
evidence must state what was found and where, in one sentence, for both pass and fail. remediation is one actionable sentence.
Keep dimension totals in mind: a new/changed check shifts its dimension's max, which shifts the overall total (currently 108, derived from ALL_CHECKS — not a number to hardcode, but a real one every maturity model change must account for).
Update the check catalog in docs/guide/measure-and-improve.md with a #### <ID> · <title> — <n> pts {#<id-lowercase>} entry, and the dimension-points table + level thresholds in docs/guide/maturity-model.md if they're affected — packages/cli/test/docs.test.ts and packages/cli/test/maturity-sync.test.ts fail otherwise.
Add a unit test in packages/cli/test/checks.test.ts (use fakeContext), and adjust fixtures if the check changes any fixture's expected level.
Consider opening the change as a Check change issue first (see .github/ISSUE_TEMPLATE/check_change.yml) if it's not already agreed — this is the highest-stakes contribution surface in the repo.

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.

1mo ago First seen · 31 lines · 0 tokens per session scan A b8c0a0ea6b67

Subscribe to this mod's changes

checks is a cursor rule published in the GitHub repository paladini/harness-score (585 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 404 tokens. 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.

Security ai-agents ai-assisted-development cli cursor cursor-plugin developer-tools

checks

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other cursor rules, from other repositories

prompt-to-asset

swamr-orchestrator

swamr-state-manager

read-xlsx

seed-phrase-handling

monobehaviour-lifecycle