AGENT SKILL

principle-minimize-reader-load

Use when shaping or reviewing code that is hard to follow, deciding whether new indirection or state is worth it, or writing output for people. Reduce the indirections and hidden mutable state a reader has to track.

License 许可
Apache-2.0
最近更新
2026-11-14
Stars
★ 1.6k
Forks
491

01 前言 Front Matter

name
principle-minimize-reader-load
description
Use when shaping or reviewing code that is hard to follow, deciding whether new indirection or state is worth it, or writing output for people. Reduce the indirections and hidden mutable state a reader has to track.
disable-model-invocation
true

03 SKILL.md 正文

Minimize reader load

Measure maintainability by how hard a reader must work to understand the code. Two separate axes set that effort: the number of hops between a question and its answer, and the amount of hidden or changeable state the reader has to keep in mind.

When it applies

Reviewing or shaping hard-to-follow code, deciding whether new indirection or new state is justified, and writing anything people will read, including verdicts and reports. It is a lens you always hold, not a procedure with preconditions.

What to do

  1. Treat line counts, cyclomatic complexity, and architectural tidiness as proxies. Reader effort is the target.
  2. Guard both axes. They vary independently. A flat file full of globals can be as hard to read as a deep stack of adapters.
  3. Delete layers whose cost exceeds their benefit: wrappers with one caller, interfaces with one implementation, and indirection added for a future that never came. Inline them.
  4. Require each layer to change the abstraction. A layer that forwards the same methods with the same arguments is pass-through, so collapse it.
  5. Prefer interfaces that hide meaningful decisions. A broad interface that conceals little forces readers to learn its surface and its internals as well.
  6. Narrow the scope of state. From most to least preferred: pure functions that return values instead of mutating, then local variables, then object fields, then module-level state, and globals last. Compute values instead of keeping copies synchronized.
  7. State each invariant one time, where data enters, and let consumers rely on it.
  8. Any new indirection or state must remove at least as much reader load somewhere else as it introduces.
  9. Apply the half-minute test: a newcomer should be able to say where a value comes from and what can change it in about thirty seconds.

Reader load is a security property. A permission check that a reviewer has to trace through four decorators and a mutable global request context is a check that reviewers stop verifying. An authorization decision a reader can find and confirm in one function is one they will actually audit.

The failure it prevents

Deep wrapper stacks, hidden global state, and invariants restated in every consumer.

Done when

The half-minute test passes.

principle-guard-the-context-window is the agent analog of this principle.

Related: principle-guard-the-context-window, principle-laziness-protocol, principle-boundary-discipline.

04 同仓库更多 Skills

hashgraph-online
hashgraph-online/awesome-codex-plugins

migrate-to-e2e

Moves an existing Playwright, Cypress, Selenium, Appium, Detox, Maestro, or TesterArmy suite to e2e one slice at a time, with the old suite running beside the new one until each ported test is proven. Keeps a MIGRATION.md progress file so any later session resumes where the last stopped. Optionally plants a defect to show both suites catch it. Use for /migrate-to-e2e, "migrate our tests to e2e", "port these Maestro flows", "move our TesterArmy tests", or when a project has an e2e config and an older suite still running.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

e2e

Writes, runs, and debugs end-to-end tests for web and mobile apps with e2e, the agentic test runner, which mixes agent.act goals with exact locator assertions on a Playwright browser or an iOS or Android device. Also drives a project's running app live over the e2e MCP server to look at a screen, check a UI change, take a screenshot or record a video, and try a locator; and runs bug bashes, parallel e2e explore runs with each bug proven by a repro test. Use when a project depends on e2e or has an e2e.config.ts, when asked for end-to-end, browser, mobile, or agentic UI tests, to check a change in the running app, to QA or bug bash an app or branch, or when an e2e run fails.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

create-verification-skill

Generate a project-local verify-<app> skill on top of e2e, so any coding agent can launch the app, check it is worth driving, exercise a feature the way a user does, keep evidence, and bug bash it. Writes the skill, a feature map with one explore charter per feature, and proves it once. Use for /create-verification-skill, "make a verification skill for this repo", or when a project has no scripted way to prove UI behavior.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

deja-search

deja-vu memory — search the user's past AI coding sessions with the deja CLI. Holds what they already settled and never wrote into the repo (naming rules, banned or already-tried tools, required checks before merge, preferred values, who owns what). Use before your first edit in a task, before you call a change done or ready to merge, before you recommend a tool, library, design or reviewer, before re-debugging an error that may already be solved, when they say 'didn't we fix this before', 'what did we decide about X' or 'I already have that', and before telling them something on this machine does not exist.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

deja-reflect

End-of-session reflection and memory curation with deja-vu. Review what was decided, what commands broke and what repaired them, and record durable project rules or decisions with deja remember so the next session starts with them.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

revid

Make, edit, export and post AI videos with Revid (revid.ai) through the Revid MCP server. Use whenever the user wants a short-form or long-form video made (from an idea, a script, a URL, an article, a PDF, a tweet, a product page, their own clips, or a song), wants to find what is going viral on TikTok, YouTube, Instagram or X before making something, wants to edit or re-export an existing Revid project, generate a standalone AI image or clip, make a series episode, or publish and schedule a finished video to connected social accounts. Covers setup (hosted MCP with OAuth, or an API key), the 36 tools, credits, polling and the rules for publishing. Routes to the more specific revid-* skills when one fits.

图像与多媒体Skill与智能体开发
★ 1.6k