rule-editor

rule-editor is a skill for Codex from Eliyce/paqad-ai. It costs 17 tokens per session (1,035 once invoked), scanned A, original, MIT.

A single entry point for adding, changing, removing, or downgrading rules in a rules-as-scripts project. It updates the rule mapping and regenerates only the scripts affected by the change.

In plain words
What is it for?
Use it when a user adds, edits, removes, or marks a rule as impossible to verify, including when a rule's generated scripts need updating.
Why use it?
It keeps rule identifiers and generated scripts synchronized while avoiding unnecessary full regeneration. Edits can also show how the resulting behavior changes.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it when a user adds, edits, removes, or marks a rule as impossible to verify, including when a rule's generated scripts need updating.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/eliyce/paqad-ai/rule-editor/github.svg)](https://agentmods.dev/skills/eliyce/paqad-ai/rule-editor)
Your own site
<a href="https://agentmods.dev/skills/eliyce/paqad-ai/rule-editor"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/rule-editor/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 rule-editor

Your own site · 80×15
<a href="https://agentmods.dev/skills/eliyce/paqad-ai/rule-editor"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/rule-editor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,035 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 warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Prompt Injection · line 26
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 $0.00017 $0.01035
Opus 5 $0.00009 $0.00517
Sonnet 5 $0.00003 $0.00207
Haiku 4.5 $0.00002 $0.00103

Measured 10d ago against content hash 81a5999e453c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

rule-editor 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 10d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/edit-rule.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-editor/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

What It Does

Owns the mutation cascade so adding, editing, or removing a rule recomputes only what changed — never a full regeneration:

Mode Effect
add Inserts the bullet into the target rule file, mints a stable RL-<hash> id, then classifies + generates scripts for only the new rule.
edit Updates the bullet text, preserves the id, regenerates only that rule's scripts, and surfaces a behavior diff via Decision Pause when scripts change.
remove Removes the bullet, moves the map entry to archived: (delayed delete); scripts pruned on the next regen pass.
downgrade Keeps the rule, deletes its scripts, flips the map entry to verifiability.kind: unverifiable with a recorded reason.

Use This When

  • A user prompt matches the priority-225 router rules add rule, edit rule, remove rule, or mark rule as unverifiable.

Inputs

  • The target rule file (for add) or the RL-<id> (for edit/remove/downgrade).
  • The new rule text (add, edit) or downgrade reason (downgrade).
  • docs/instructions/rules/rule-script-map.yml (written only via the bundled wrapper → src/rule-scripts/apply.ts).

Procedure

  1. Apply the deterministic mechanics:
    node scripts/edit-rule.mjs add       <project-root> <source-rel> "<text>"
    node scripts/edit-rule.mjs edit      <project-root> RL-<id> "<text>"
    node scripts/edit-rule.mjs remove    <project-root> RL-<id>
    node scripts/edit-rule.mjs downgrade <project-root> RL-<id> "<reason>"
    
  2. For add and edit: re-run analyze rules (idempotent — touches only the changed rule) then generate rule scripts with only_rule_id set to the affected id, so only that rule's scripts are regenerated.
  3. For edit, diff the regenerated scripts against the prior ones; if behavior changed, surface a Decision Pause packet before accepting.
  4. Present a ## Rule Change Summary naming the id, the mode, and any scripts added/removed.

Read the full file on GitHub · 76 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. 10d ago First seen · 76 lines · 17 tokens per session scan A 81a5999e453c

Subscribe to this mod's changes

rule-editor is a skill published in the GitHub repository Eliyce/paqad-ai (8 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 1,035 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.