rule-script-runner

rule-script-runner is a skill for Codex from Eliyce/paqad-ai. It costs 49 tokens per session (850 once invoked), scanned A, original, MIT.

An automated check stage that runs registered rule scripts against changed files and combines their findings into a report. Deterministic findings can block strict checks, while heuristic findings are sent for human or review-stage consideration.

In plain words
What is it for?
Use it as part of feature-development checks when rule compliance is configured to warn or block.
Why use it?
It applies project rules consistently and reuses results when the relevant files have not changed. Missing command-line dependencies are reported cleanly instead of crashing the stage.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it as part of feature-development checks when rule compliance is configured to warn or block.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/eliyce/paqad-ai/rule-script-runner
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.

Any agent
npx skills add Eliyce/paqad-ai --skill rule-script-runner
Clone the repo
git clone --depth 1 https://github.com/Eliyce/paqad-ai

Made for: Codex.

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 rule-script-runner

README.md
[![agentmods](https://agentmods.dev/badge/skills/eliyce/paqad-ai/rule-script-runner.svg)](https://agentmods.dev/skills/eliyce/paqad-ai/rule-script-runner)
Your own site
<a href="https://agentmods.dev/skills/eliyce/paqad-ai/rule-script-runner"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/rule-script-runner.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 850 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00049 $0.00850
Opus 5 $0.00024 $0.00425
Sonnet 5 $0.00010 $0.00170
Haiku 4.5 $0.00005 $0.00085

Measured 8d ago against content hash 7161524f300b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

rule-script-runner 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/run.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

runtime/base/skills/rule-script-runner/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

What It Does

During feature-development.checks, runs every script registered in docs/instructions/rules/rule-script-map.yml against the changed files (diff-scoped) and aggregates the findings:

  • deterministic findings → block the checks stage under mode: strict.
  • heuristic findings → informational; routed to the review stage alongside adversarial-review. They never block.
  • A script declaring requires.binaries that are missing emits a clean "missing dependency" result and is skipped — it never crashes the stage.

Results are written to .paqad/scripts/rules/.cache/report.json, hash-cached on rule_files_hash × script_files_hash × target_files_hash so unchanged inputs re-use the cached report.

Use This When

  • Invoked from feature-development.checks after the project command checks, when checks.rule_compliance.mode is warn or strict.
  • Never invoked directly by the user; it is a workflow sub-step.

Inputs

  • docs/instructions/rules/rule-script-map.yml (read-only).
  • The registered .paqad/scripts/rules/**/*.mjs scripts.
  • The changed-files list (diff) for scope: changed-files; whole-tree enumeration otherwise.
  • checks.rule_compliance.mode from feature-development.yaml.

Procedure

  1. Read checks.rule_compliance.mode from feature-development.yaml. If off, skip entirely.
  2. Run the runner:
    node scripts/run.mjs <project-root> <mode> [changed-file ...]
    
    Exit 0 = stage may proceed. Exit 1 = mode: strict and a deterministic finding blocks the stage.
  3. Surface blocking deterministic findings as the stage failure with file:line and message. Pass heuristic findings to the review stage.

Output Contract

  • .paqad/scripts/rules/.cache/report.json written (or re-used from cache).
  • JSON RunReport on stdout: results, counts (deterministic / heuristic / skipped), and blocking.
  • Non-zero exit only when mode: strict and at least one deterministic finding exists.

Escalate / Stop Conditions

Read the full file on GitHub · 72 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 72 lines · 49 tokens per session scan A 7161524f300b

Subscribe to this mod's changes

rule-script-runner is a skill published in the GitHub repository Eliyce/paqad-ai (8 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 850 once invoked, about $0.0002 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.