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-runnergit 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-runner)<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>- 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 | $0.00049 | $0.00850 |
| Opus 5 | $0.00024 | $0.00425 |
| Sonnet 5 | $0.00010 | $0.00170 |
| Haiku 4.5 | $0.00005 | $0.00085 |
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.
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 — 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:
deterministicfindings → block thechecksstage undermode: strict.heuristicfindings → informational; routed to thereviewstage alongsideadversarial-review. They never block.- A script declaring
requires.binariesthat 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.checksafter the project command checks, whenchecks.rule_compliance.modeiswarnorstrict. - 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/**/*.mjsscripts. - The changed-files list (diff) for
scope: changed-files; whole-tree enumeration otherwise. checks.rule_compliance.modefromfeature-development.yaml.
Procedure
- Read
checks.rule_compliance.modefromfeature-development.yaml. Ifoff, skip entirely. - Run the runner:
Exit 0 = stage may proceed. Exit 1 =node scripts/run.mjs <project-root> <mode> [changed-file ...]mode: strictand adeterministicfinding blocks the stage. - Surface blocking
deterministicfindings as the stage failure with file:line and message. Passheuristicfindings to thereviewstage.
Output Contract
.paqad/scripts/rules/.cache/report.jsonwritten (or re-used from cache).- JSON
RunReporton stdout:results,counts(deterministic / heuristic / skipped), andblocking. - Non-zero exit only when
mode: strictand at least onedeterministicfinding exists.
Escalate / Stop Conditions
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.
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.
- 8d ago First seen · 72 lines · 49 tokens per session scan A 7161524f300b
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.
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.
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.
database-verification
Shell-based database connectivity and integrity checks. Verifies that databases are reachable, schemas match expectations, and data integrity constraints hold.
coverage-analysis
Running coverage tools, interpreting coverage reports, identifying high-risk gaps, and prioritizing which uncovered code to test first.