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.
npx skills add Eliyce/paqad-ai --skill rule-script-generatorgit clone --depth 1 https://github.com/Eliyce/paqad-aiWrote 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.
[](https://agentmods.dev/skills/eliyce/paqad-ai/rule-script-generator)<a href="https://agentmods.dev/skills/eliyce/paqad-ai/rule-script-generator"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/rule-script-generator/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.
<a href="https://agentmods.dev/skills/eliyce/paqad-ai/rule-script-generator"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/rule-script-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00041 | $0.01302 |
| Opus 5 | $0.00020 | $0.00651 |
| Sonnet 5 | $0.00008 | $0.00260 |
| Haiku 4.5 | $0.00004 | $0.00130 |
Grade A, and why
rule-script-generator 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What It Does
For every rule in rule-script-map.yml whose verifiability.kind ∈ {deterministic, heuristic} and whose enforced_by is empty, authors one or more Node ESM scripts under .paqad/scripts/rules/<mirror>/<rule-file>/NNN-name.mjs, each with __fixtures__/pass/ and __fixtures__/fail/. Each script:
- Carries the
@paqad-rule-scriptheader (validated against the header schema). - Reads
{ projectRoot, files }from stdin and writes the findings JSON contract to stdout. - Is validated against its own fixtures before registration. Pass fixtures must yield zero findings; fail fixtures at least one. A script that fails is rejected and surfaced — never registered.
No .sh scripts are ever produced. See references/script-authoring.md for the full contract.
Use This When
- A user prompt matches the priority-225 router rules
generate rule scriptsorregenerate scripts for rule RL-<id>. - After
analyze ruleshas produced a reviewedrule-script-map.yml.
Inputs
docs/instructions/rules/rule-script-map.yml(read for rules + classifications; written only via the bundledregister-script.mjs→src/rule-scripts/apply.ts).- The rule text for each target rule (to author the detection logic).
- Existing in-scope source files, used for the over-flagging dry-run guard.
Procedure
- Load the map. Select target rules:
kind ∈ {deterministic, heuristic}andenforced_by == []. Ifonly_rule_idis set, restrict to it. - For each target rule, author
NNN-name.mjswith the header + stdin/stdout contract (references/script-authoring.md), plus 2–4 synthetic 5–15 line fixtures under__fixtures__/pass/and__fixtures__/fail/. Fixtures are synthetic — never copied from the user's real code. - Validate the script against its fixtures:
Exit 0 = accepted. Exit 1 = rejected: surface a Decision Pause packet ("scriptnode scripts/validate-script.mjs <abs-script-path>NNN-name.mjsfailed its own fixtures — regenerate / edit / mark unverifiable?") and do not register. - Over-flag dry-run: run the accepted script across in-scope existing files. If the flag rate exceeds the per-kind threshold (
deterministic: 0.05,heuristic: 0.20), surface a Decision Pause packet before registering. - Register the validated script onto its rule:
node scripts/register-script.mjs <project-root> <script-path-rel> <rule-id> <kind> <scope> - At the end of the cycle, prune orphaned scripts (left by edited / downgraded / removed rules):
Deletes anynode scripts/prune.mjs <project-root>.mjs+__fixtures__/under.paqad/scripts/rules/not referenced by an active map rule. Archived rules' scripts survive one cycle, then this prunes them. - Present the
## Generation Summary: scripts accepted, scripts rejected (with reasons), over-flag warnings, pruned files. Tell the user the next prompt (feature-developmentwill now enforce them).
What ships with it
5 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.
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.
- 9d ago First seen · 86 lines · 41 tokens per session scan A e91a9f6788f3
rule-script-generator is a skill published in the GitHub repository Eliyce/paqad-ai (8 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 1,302 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.
Other skills, from other repositories
auto-qa
QAMESH project QA mesh — plan, run, report, and publish deterministic QA evidence.
auto-canary
A deployment health-check skill for testing whether a recently deployed or staging website is working. It runs build, end-to-end, and browser checks, then reports a pass, warning, or failure.
tdd
A Test-Driven Development guide. TDD means writing a failing test first, adding the smallest implementation that passes it, and then improving the code while keeping the tests passing.
database-verification
Shell-based database connectivity and integrity checks. Verifies that databases are reachable, schemas match expectations, and data integrity constraints hold.
testing-strategy
A testing guide that explains how to combine unit, integration, contract, and end-to-end tests. End-to-end tests check complete user flows, while integration tests check components working together.
coverage-analysis
Running coverage tools, interpreting coverage reports, identifying high-risk gaps, and prioritizing which uncovered code to test first.