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 agentmods add skills/melodic-software/claude-code-plugins/script-the-deterministic-worknpx skills add melodic-software/claude-code-plugins --skill script-the-deterministic-workgit clone --depth 1 https://github.com/melodic-software/claude-code-pluginsWrote 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/melodic-software/claude-code-plugins/script-the-deterministic-work)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/script-the-deterministic-work"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/script-the-deterministic-work.svg" alt="Measured on agentmods" 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 | $0.00190 | $0.02049 |
| Opus 5 | $0.00095 | $0.01025 |
| Sonnet 5 | $0.00038 | $0.00410 |
| Haiku 4.5 | $0.00019 | $0.00205 |
Grade A, and why
script-the-deterministic-work 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 yesterday.
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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Script the deterministic work
A drift corrector for the discipline of offloading deterministic sub-work to
a script instead of performing it in your head. The method, re-anchor, audit
the work in flight, correct forward, report, and the tone that firing this is
not an accusation, lives in
${CLAUDE_PLUGIN_ROOT}/context/re-anchor-audit-correct.md.
Read it; this file adds only what is specific to scripting deterministic work.
The discipline this re-anchors
When a sub-task is purely deterministic. Its answer follows mechanically from its input with no judgement in the middle. Write a script (or invoke a tool) that produces the answer, run it, read the output, and reason only after, over that output. Counting, diffing, sorting, transforming, matching, sweeping across files, and arithmetic are the recurring shapes. The model is a poor calculator and a worse line-counter; a hand-tallied count or an eyeballed diff carries a silent error the script would not.
The boundary of what to script is not "anything tedious". It is set by which enforcement tier the sub-work belongs to.
The tier vocabulary, a standards convention owns this
The source of truth for the tier distinction is the consuming organization's enforceability-tiers convention, which classifies work by who can decide it. Resolve it per the method doc's ladder, the consumer's own instruction layer first, then that standards convention, then the portable baseline below. And re-anchor the distinction rather than restating the doc's criteria:
- Deterministic, the answer is pass/fail, exact, or countable with no judgement. Script it, run it, reason over the output. This is the core of the discipline.
- Detect-then-judge, a mechanical pass narrows the candidates, but the verdict needs meaning or context. Script only the detect half; the judgement stays with the model. A script's flag is a candidate, never the ruling.
- Reasoning-only. Meaning, intent, fit, abstraction quality. Never script it. A script here manufactures false confidence. It dresses a judgement call as a computed fact.
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.
- yesterday First seen · 155 lines · 190 tokens per session scan A b909d3cb1a51
script-the-deterministic-work is a skill published in the GitHub repository melodic-software/claude-code-plugins (14 stars, last pushed yesterday), licensed MIT. It adds 190 tokens to every session and 2,049 once invoked, about $0.0010 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 2026-09-03.
Other skills, from other repositories
phpunit-migration-test-reviewing
Internal sub-skill. Do not auto-activate. Use only when explicitly invoked by name by another skill or agent.
structuring-documentation
Use when writing, editing, auditing, splitting, or measuring Markdown documentation surfaces — README.md, AGENTS.md, CLAUDE.md, and docs/ siblings. Triggers include "is this doc too long", "split this README", "measure the docs", "where does this documentation belong", "audit the documentation", and any request to…
phpunit-unit-test-writing
Use this skill when the user asks to write, generate, create, or add PHPUnit unit tests for a Shopware 6 source class — phrases like "write unit tests for X", "generate tests for ClassName", "create PHPUnit tests", "add test coverage", "test this class", "cover this with tests", "I need tests for", "unit test this"…
phpunit-migration-test-generation
Use this skill when the user asks to generate, write, or create migration tests for a Shopware 6 migration class — phrases like "generate migration tests", "write a migration test", "create migration test", "test this migration", "test Migration1234Foo". Analyzes the source migration's SQL operations to pick an…
phpunit-test-reconciling
Internal sub-skill. Do not auto-activate. Use only when explicitly invoked by name by another skill or agent.
release-info-writing
Use this skill when the user is completing features, deprecations, or breaking changes in the Shopware core repository that affect external developers, or when they ask to write release info, upgrade entries, release notes, release documentation, or changelog entries — phrases like "write a release info entry for my…