codehydra: Skill for Claude Code

.claude/skills/config-key/SKILL.md

config-key is a skill for Claude Code from stefanhoelzl/codehydra. It costs 76 tokens per session (1,074 once invoked), scanned A, original, MIT.

A procedure for adding or changing a CodeHydra configuration or saved-state setting, including its type, default, validation, and migration behavior.

In plain words
What is it for?
Use it when registering, renaming, deprecating, removing, or changing a configuration or persisted state key.
Why use it?
It helps keep settings consistent across configuration files, environment variables, command-line flags, the settings screen, and saved application state.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is stefanhoelzl/codehydra's own configuration. It tells Claude Code how to work on codehydra itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything codehydra configures →

Reuse

Borrowing it

Nothing to install: this file belongs to stefanhoelzl/codehydra. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/stefanhoelzl/codehydra/main/.claude/skills/config-key/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/stefanhoelzl/codehydra

Made for: Claude Code.

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 config-key

README.md
[![agentmods](https://agentmods.dev/badge/skills/stefanhoelzl/codehydra/config-key/github.svg)](https://agentmods.dev/skills/stefanhoelzl/codehydra/config-key)
Your own site
<a href="https://agentmods.dev/skills/stefanhoelzl/codehydra/config-key"><img src="https://agentmods.dev/badge/skills/stefanhoelzl/codehydra/config-key/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 config-key

Your own site · 80×15
<a href="https://agentmods.dev/skills/stefanhoelzl/codehydra/config-key"><img src="https://agentmods.dev/badge/skills/stefanhoelzl/codehydra/config-key.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,074 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 $0.00076 $0.01074
Opus 5.5 $0.00030 $0.00430
Sonnet 5.5 $0.00015 $0.00215
Haiku 4.5 $0.00008 $0.00107

Measured 4d ago against content hash 5e5def4fa174, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

config-key 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 4d 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.

.claude/skills/config-key/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Config / state key

Reference: docs/CONFIGURATION.md. Code: src/boundaries/platform/config.ts, state-service.ts, persisted-store.ts, store-definition.ts (types, builders, semantics in JSDoc).

1. Pick the store

  • Config (config.json, env, CLI; user-authored) — deps.configService.register(...) / deps.config.register(...).
  • State (state.json; the app writes it at runtime, no env/CLI, no computedDefault) — deps.stateService.register(...). Loaded in app:start → init (state-module.ts): read it in start or later, never at construction.

2. Register in the owning module's factory

const fooConfig = deps.configService.register("area.foo-bar", {
  default: 30,
  description: "What it does (shown in --help, settings, ch config list)",
  applies: "live", // or omit = "restart"; settings-UI hint only
  ...storeNumber({ min: 1 }),
});
  • Key: dot-separated, kebab-case. Keep the returned typed accessor; never read by string key. Read .get() where the value is used (not cached) if applies: "live".
  • Owned by no single module → register in src/main.ts beside agent and thread the accessor in.
  • Builder (store-definition.ts): storeBoolean(), storeNumber({min,max,integer}), storeEnum([...], {nullable: true}?), storeEnumList([...]), storeString({nullable: true}?), storeFolder() (absolute path), storeCustom({parse, validate, validValues?, settingsControl?}) (JSON/structured values). parse takes the raw env/CLI string, validate the JSON value; return undefined for invalid — the app then refuses to start with a message naming the key.
  • computedDefault: (ctx) => … | undefined for build-dependent defaults (Config only; ctx.isDevelopment, ctx.isPackaged).

3. Exposure and secrets

  • The builder attaches a settingsControl; that alone puts a Config key in the settings dialog and ch config (isUserSetting). Override it (e.g. { kind: "string" }, guarded-text, text with helpPanel) or, for storeCustom, pass none to keep the key hidden. CLI-only actions go in NON_SETTING_KEYS.
  • redact: true (or (value, token) => projection, must not throw) for secrets — masked in the settings field, ch config, bug reports, telemetry.
  • omit: true for values edited in the clear that must stay out of diagnostics (plugins.config).

Read the full file on GitHub · 54 lines

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. 4d ago First seen · 54 lines · 76 tokens per session scan A 5e5def4fa174

Subscribe to this mod's changes

config-key is a skill published in the GitHub repository stefanhoelzl/codehydra (20 stars, last pushed today), licensed MIT. It adds 76 tokens to every session and 1,074 once invoked, about $0.0003 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 2026-10-26.

Related

Other skills, from other repositories

peer-review

Structured manuscript/grant review with checklist-based evaluation. Use when writing formal peer reviews with specific criteria methodology assessment, statistical validity, reporting standards compliance (CONSORT/STROBE), and constructive feedback. Best for actual review writing, manuscript revision. For evaluating…

xintaofei/codeg · 71 tokens

scientific-critical-thinking

Evaluate scientific claims and evidence quality. Use for assessing experimental design validity, identifying biases and confounders, applying evidence grading frameworks (GRADE, Cochrane Risk of Bias), or teaching critical analysis. Best for understanding evidence quality, identifying flaws. For formal peer review…

xintaofei/codeg · 63 tokens

scientific-schematics

Create publication-quality scientific diagrams using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.1 Pro Preview for quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways…

xintaofei/codeg · 68 tokens

hypothesis-generation

Structured hypothesis formulation from observations. Use when you have experimental observations or data and need to formulate testable hypotheses with predictions, propose mechanisms, and design experiments to test them. Follows scientific method framework. For open-ended ideation use scientific-brainstorming; for…

xintaofei/codeg · 69 tokens

paper-lookup

Search 10 academic literature APIs for papers, preprints, citations, and open-access full text, and return results with reproducible provenance. Covers PubMed, PMC (full text), bioRxiv, medRxiv, arXiv, OpenAlex, Crossref, Semantic Scholar, CORE, Unpaywall. Use when searching for papers, citations, DOI/PMID/arXiv…

xintaofei/codeg · 146 tokens

scholar-evaluation

Systematically evaluate scholarly work using the ScholarEval framework, providing structured assessment across research quality dimensions including problem formulation, methodology, analysis, and writing with quantitative scoring and actionable feedback.

xintaofei/codeg · 40 tokens