agentmods.dev

script-skill

script-skill is a skill for Claude Code, Codex from lorem-dev/skillkeeper-test-repo. It costs 17 tokens per session (415 once invoked), scanned A, original, MIT.

A skill package that declares which bundled scripts should receive executable permissions during installation. It also specifies how the package's guidance file is selected.

In plain words
What is it for?
It is for validating executable-file manifests, selective `+x` permissions, uninstall cleanup, and choosing between `GUIDE.md` and `RULES.md`.
Why use it?
It ensures only the listed scripts become runnable and tests that installation, permissions, and guidance-file fallback behave as intended.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 2repo 2mo ago A scan 17 tokens original MIT

Good fit It is for validating executable-file manifests, selective +x permissions, uninstall cleanup, and choosing between GUIDE.md and RULES.md.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lorem-dev/skillkeeper-test-repo/script-skill
View source ↗ lorem-dev/skillkeeper-test-repo
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 lorem-dev/skillkeeper-test-repo --skill script-skill
Clone the repo
git clone --depth 1 https://github.com/lorem-dev/skillkeeper-test-repo

Made for: Claude Code, 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 script-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/lorem-dev/skillkeeper-test-repo/script-skill/github.svg)](https://agentmods.dev/skills/lorem-dev/skillkeeper-test-repo/script-skill)
Your own site
<a href="https://agentmods.dev/skills/lorem-dev/skillkeeper-test-repo/script-skill"><img src="https://agentmods.dev/badge/skills/lorem-dev/skillkeeper-test-repo/script-skill/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 script-skill

Your own site · 80×15
<a href="https://agentmods.dev/skills/lorem-dev/skillkeeper-test-repo/script-skill"><img src="https://agentmods.dev/badge/skills/lorem-dev/skillkeeper-test-repo/script-skill.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 415 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00017 $0.00415
Opus 5.5 $0.00007 $0.00166
Sonnet 5.5 $0.00003 $0.00083
Haiku 4.5 $0.00002 $0.00042

Measured 2mo ago against content hash 56b69931337e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

script-skill 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 2mo ago.

The scan reads SKILL.md. This mod also ships 3 executable files (bin/check.py, bin/run.sh, lib/shared.sh), 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.

script-skill/SKILL.md · 38 lines

What it actually says

script-skill

What this fixture covers:

  • The executables manifest field. Paths are skill-relative, not repository-relative: bin/run.sh, never script-skill/bin/run.sh.
  • Selective +x. After install, bin/run.sh and bin/check.py must be executable, and lib/shared.sh must not be - it is deliberately left out of the list. That contrast is the whole point of shipping a third script.
  • +x being applied, not inherited. All three scripts are committed with mode 644, so the executable bit on the two declared paths can only come from install acting on the executables list. Keep them 644 in the repository: a 755 source mode would make this fixture unable to tell the two mechanisms apart.
  • Two files in one subdirectory plus one file in another, so the uninstall path has more than one empty directory to prune.
  • RULES.md as the fallback. This skill ships RULES.md and no GUIDE.md, so RULES.md is what reaches the agent's guidance file. Compare with documented-skill, where GUIDE.md wins because both exist.

Note that the configured executable globs are a separate mechanism: a path can also become executable by matching a glob from SkillKeeper's own configuration, without being named here. lib/shared.sh stays non-executable only as long as no configured glob matches it.

The scripts do nothing but print a line. Running a skill is the agent's job; SkillKeeper only installs files and edits config regions.

Files

What ships with it

4 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. 2mo ago First seen · 38 lines · 17 tokens per session scan A 56b69931337e

Subscribe to this mod's changes

script-skill is a skill published in the GitHub repository lorem-dev/skillkeeper-test-repo (2 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 415 once invoked, about $0.0001 per session on Opus 5.5. 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.

aiai-skillsmcp
Related

script-skill compared with skills from other repositories

script-skill next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
script-skilllorem-dev/skillkeeper-test-repoSkill22mo agoMITA17Claude Code, Codex
pcbwayaklofas/kicad-happySkill1.6ktodayMITA119Claude Code
asc-subscription-localizationrorkai/app-store-connect-cli-skillsSkill1.1ktodayMITA60Claude Code
happiness-skillkangarooking/cangjie-skillSkill12k1mo agoMITA136Claude Code, Codex
remotion-best-practicesguanyang/open-agent-hubSkill986todayMITA116Claude Code
influence-psychologywondelai/skillsSkill2.6k5d agoMITA156Claude Code
jobs-to-be-donewondelai/skillsSkill2.6k5d agoMITA137Claude Code