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 stark-ai-de/agent-skills --skill script-simplificationgit clone --depth 1 https://github.com/stark-ai-de/agent-skillsWrote 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/stark-ai-de/agent-skills/script-simplification)<a href="https://agentmods.dev/skills/stark-ai-de/agent-skills/script-simplification"><img src="https://agentmods.dev/badge/skills/stark-ai-de/agent-skills/script-simplification/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/stark-ai-de/agent-skills/script-simplification"><img src="https://agentmods.dev/badge/skills/stark-ai-de/agent-skills/script-simplification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00062 | $0.01400 |
| Opus 5.5 | $0.00025 | $0.00560 |
| Sonnet 5.5 | $0.00012 | $0.00280 |
| Haiku 4.5 | $0.00006 | $0.00140 |
Grade A, and why
script-simplification 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 6d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Script Simplification
Goal
Reduce the number of mechanisms a maintainer must understand while preserving the behavior and safeguards that callers rely on. A shorter diff alone is not evidence of improvement.
When to use
- The user asks to simplify, consolidate, or remove repository scripts or CLI entry points.
- A script duplicates a workflow, package command, generated wrapper, or standard tool and its actual use needs checking.
- Several repositories need separately reviewable script cleanup.
When not to use
- The task is only runtime performance tuning, dependency updates, or a broad health audit without a script-maintenance goal.
- A focused failed pipeline needs diagnosis first; use the repository's CI debugging workflow.
- A change primarily decides architecture or moves runtime ownership; use the repository's architecture workflow before script cleanup.
- The only proposed change is a language port, line-count reduction, or new helper framework with no demonstrated maintenance benefit.
Workflow selection
The complete workflow set is:
assess: inventory scripts and recommend changes without writing files or invoking write-capable checks.simplify: implement and validate a bounded script cleanup that the user already authorized.
For clear authorized intent, announce the selected route and scope and proceed.
An assessment, review, or recommendation request selects assess, not
simplify. On bare activation, ambiguous cleanup intent, or an options request,
show both workflows and ask; an options request alone authorizes no execution.
Do not infer merge, deployment, publication, tool installation, or external
operations from permission to edit scripts or create a PR. Preserve host Plan
and no-write controls. The steps below stay within the selected route.
Inputs to inspect
- User scope and authorization; exact repository, default branch, worktree, uncommitted changes, and repository instructions or accepted decisions.
- Script files and generated sources, package commands, CI and release jobs, docs, runbooks, operator commands, and tests that invoke them.
- Required outputs, side effects, authentication, ownership, size/time bounds, concurrency behavior, error handling, and pinned tool versions.
What ships with it
1 file 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.
- 6d ago First seen · 143 lines · 62 tokens per session scan A b3e2e73c2a14
script-simplification is a skill published in the GitHub repository stark-ai-de/agent-skills (8 stars, last pushed today), licensed Apache-2.0. It adds 62 tokens to every session and 1,400 once invoked, about $0.0002 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 2026-10-10.
Other skills, from other repositories
cancel
Cancel an active tracked Claude Code job in this repository. Args: [job-id]. Use only when the user wants to stop a queued or running Claude Code job.
eco-max
Maximum-savings variant of eco - the same frugality rules with a tighter reply budget, for routine chores (rename, small fix, quick lookup, boilerplate). Prefer plain eco for hard or high-stakes work. Works in any language.
keeping-docs-alive
Use whenever you finish a task, pause a session, complete a phase, or change the project status. Ensures the living docs (the active plan and CLAUDE.md Section 5) reflect the real state so the next session can resume without loss of context. Auto-activates on "done", "pausing", "completed", "end of phase", "I'm going…
next
Recommend the next one to three concrete actions with the highest leverage for the latest actionable result or current Binding. Use only when the user invokes next or asks what to do next; never redirect or act silently.
eco
Token-frugal mode for Codex - fewer tokens per turn at full task quality. Use when the user mentions tokens, cost, budget, quota, rate limits, or working economically, in any language. Say nothing about invoking it - read this file, then let your first visible action be the work. Pass "setup" to configure durable…
eco-long-body
Token-frugal mode for Codex - minimize token spend (no preamble turns, no unasked surveys, region reads, batched shell calls) at full task quality. Use when the user mentions tokens, cost, budget, quota, rate limits, or economical operation, in any language. Invoke once; applies for the rest of the thread. Pass…