Agent skill

Prism Maintain

by irfndi in irfndi/prism-liquidity-agent

Maintain the Prism codebase: measure cyclomatic complexity, refactor hotspots, and enforce the anti-slop type discipline.

MITAuto-check passedWriting & Content

Install Prism Maintain

skills CLI
$ npx skills add irfndi/prism-liquidity-agent --skill prism-maintain -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install irfndi/prism-liquidity-agent prism-maintain --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/irfndi/prism-liquidity-agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/prism-maintain .claude/skills/prism-maintain && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
prism-maintain
GitHub stars
123
Token cost
~1k tokens
SKILL.md length
362 words
Files
1
Skills in repo
4
Repo updated
First seen
Licence
MIT

At a glance

Maintain the Prism codebase: measure cyclomatic complexity, refactor hotspots, and enforce the anti-slop type discipline.

  • Works in 5 steps: Measure the touched functions, rank by… → Report hotspots with numbers BEFORE… → Refactor worst first, one function at a… → …
  • The user asks about complexity
  • SKILL.md covers Complexity gates (project…, Workflow (mandatory), Refactor tactics (preference… and When NOT to split, plus 1 more section
  • Calls bun and bunx

What it does

Prism Maintain is an agent skill from irfndi/prism-liquidity-agent. Maintain the Prism codebase: measure cyclomatic complexity, refactor hotspots, and enforce the anti-slop type discipline. Use when the user asks about "complexity", "refactor", "hotspot", "maintainability", "code health", "anti-slop", "lint rules", or "clean up" the Prism repo.

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: Requires Bun 1.4+ and oxlint with the vendored anti-slop plugin.

It sits in Writing & Content, covering Humanizing AI text, Code quality and Refactoring. The repository describes itself as: Autonomous LP trading agent - auto-rebalancing with backtested strategies - Currently support Meteora DLMM. The licence is MIT.

When your agent uses it

  • The user asks about complexity
  • Maintainability
  • Clean up the Prism repo

Example prompts

  • “complexity”
  • “refactor”
  • “hotspot”
  • “/prism-maintain”

Requirements

  • Compatibility (from SKILL.md): Requires Bun 1.4+ and oxlint with the vendored anti-slop plugin.

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Measure the touched functions, rank by CCN descending.
  2. Report hotspots with numbers BEFORE touching anything.
  3. Refactor worst first, one function at a time.
  4. Re-measure; close with the report table below.
  5. Verify: bun run lint, bun run format, full bun run test green with

What it can do on your machine

Read from SKILL.md and the folder at commit d15c63e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • bun
    • bunx

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    Requires Bun 1.4+ and oxlint with the vendored anti-slop plugin.

    From compatibility in the SKILL.md frontmatter.

Context cost

Prism Maintain loads about 1k tokens when it runs. Until then it costs about 73 tokens; SKILL.md has 362 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~73
When it runs · the whole SKILL.md, loaded when a task matches
~1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from irfndi/prism-liquidity-agent at commit d15c63e, republished under its MIT licence (© irfndi). 362 words, ~1,037 tokens.

Download SKILL.mdSave it as .claude/skills/prism-maintain/SKILL.md (or your agent's skills folder).
name
prism-maintain
description
Maintain the Prism codebase: measure cyclomatic complexity, refactor hotspots, and enforce the anti-slop type discipline. Use when the user asks about "complexity", "refactor", "hotspot", "maintainability", "code health", "anti-slop", "lint rules", or "clean up" the Prism repo.
compatibility
Requires Bun 1.4+ and oxlint with the vendored anti-slop plugin.
version
0.1.0
license
MIT
author
irfndi
homepage
https://github.com/irfndi/prism-liquidity-agent
tags
typescript, effect-ts, refactoring, complexity, lint, maintainability

Prism Code Maintenance

Measure complexity, refactor hotspots, keep the code human-maintainable. Methodology adapted from saurabhkumar8112/cyclomatic-complexity-skill (Apache-2.0); type discipline enforced by the vendored dmmulroy/anti-slop v0.1.2 plugin in tools/oxlint/anti-slop/.

Complexity gates (project config wins)

bun run lint enforces complexity: max 10 as an error via oxlint (type-aware — it is the authoritative measure for this Effect-TS codebase; line-counters like lizard mis-parse Effect.gen chains and report phantom CCN 50+ on 15-line functions, so never act on lizard numbers here).

Bands: 1–6 fine · 7–10 watch (refactor only if touching the function anyway) · 11+ must split before merge (lint fails).

Watch-band probe (never commit this config):

bash
sed '"'"'s/"max": 10/"max": 6/'"'"' .oxlintrc.json > .oxlint-cc6.json
bunx oxlint --config .oxlint-cc6.json engine ops bench cli
rm .oxlint-cc6.json

Workflow (mandatory)

  1. Measure the touched functions, rank by CCN descending.
  2. Report hotspots with numbers BEFORE touching anything.
  3. Refactor worst first, one function at a time.
  4. Re-measure; close with the report table below.
  5. Verify: bun run lint, bun run format, full bun run test green with ZERO test edits (unchanged tests passing is the behavior proof).
md
## Complexity report
| Function | Before | After |
|----------|--------|-------|
| runPoolEntryGates | 11 | 9 |
Extracted: isSafetyBinsSkippable, snapshotPriceDrift
Behavior verified: full suite green, no test edits

Refactor tactics (preference order)

  1. Guard clauses — invert, return early, kill nesting.
  2. Extract function — name for WHAT, not how.
  3. Lookup table / map over if-else chains.
  4. Named predicates — isPositiveFiniteApr(x) beats boolean soup.
  5. Lookup before polymorphism: Effect code dispatches via Layers and tagged unions, not class hierarchies.
  6. continue over nested if in loops.

Hard rules: preserve behavior · never game the metric (a dense one-liner hiding 6 branches is worse than the honest chain) · never break exported signatures without asking · one responsibility per function.

Show full SKILL.md (116 more words)Show less

When NOT to split

  • Numbered risk-gate chains (engine/risk-service.ts): sequential early-return blocks are the documented convention (AGENTS.md) — splitting scatters the gate narrative.
  • Single decision-loop Effect.gen blocks (engine/program.ts): splitting obscures per-cycle sequencing; extract pure predicates instead.
  • Agent-overlay handlers and network retry logic in untouched domains.

Anti-slop plugin (vendored v0.1.2 parity)

Source: tools/oxlint/anti-slop/ (.ts sources + index.mjs bundles + upstream *.test.ts contracts, which need oxlint/plugins-dev to execute). Rebuild bundles after any source change — never hand-edit .mjs:

bash
bun build tools/oxlint/anti-slop/index.ts --outfile tools/oxlint/anti-slop/index.mjs
bun build tools/oxlint/anti-slop/effect/index.ts --outfile tools/oxlint/anti-slop/effect/index.mjs

Rules that most often bite: no-known-value-widening (open-dict annotations — prefer finite type contracts, satisfies, accumulators, or Map), require-safety-comment-for-type-assertion (every as needs a SAFETY: justification with non-empty text), no-unknown-parameters / no-unknown-returns (parse at the boundary, return named domain types). Never suppress or weaken a rule — fix the code.

© irfndi, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/prism-maintain of irfndi/prism-liquidity-agent.

Open the folder on GitHubat commit d15c63e

Compare with similar skills

Prism Maintain next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Prism Maintain compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Prism Maintain this skillirfndi/prism-liquidity-agent123—~1kAutomated safety check: PassMIT
Code Quality Gatefengshao1227/ccg-workflow5.9k—~593Automated safety check: NotesMIT
DeslopMrZoyo/deslop-GPT137—~4kAutomated safety check: PassMIT
Deslopsanity-io/sanity6.4k6 repos~180Automated safety check: PassMIT
Uncle Bob Craftsickn33/agentic-awesome-skills47k2 repos~2.6kAutomated safety check: PassMIT
AI Indexmizchi/skills359—~3.6kAutomated safety check: PassNone

Similar skills

  • Code Quality Gate

    fengshao1227/ccg-workflow

    Scans code for complexity, long functions, duplicated blocks, naming problems and code smells with a Node script, then reports and suggests refactors.

    5.9k GitHub stars~593 tokensUpdated 24 days ago
    DevelopmentAuto-check: notes
  • Deslop

    MrZoyo/deslop-GPT

    Audit or apply evidence-backed, test-first subtractive cleanup for accumulated agent-created test bloat, verification theater, and defensive or fallback bloat while preserving independent external…

    137 GitHub stars~4k tokensUpdated 3 days ago
    Writing & ContentAuto-check passed
  • Deslop

    sanity-io/sanity

    Official

    Remove AI-generated code slop and clean up code style. An agent skill from sanity-io/sanity.

    6.4k GitHub starsUsed in 6 repos~180 tokens
    Writing & ContentAuto-check passed
  • Uncle Bob Craft

    sickn33/agentic-awesome-skills

    A skill your agent uses when performing code review, writing or refactoring code, or discussing architecture; complements clean-code and does not replace project linter/formatter.

    47k GitHub starsUsed in 2 repos~2.6k tokens
    DevelopmentAuto-check passed
  • AI Index

    mizchi/skills

    Method and tooling for measuring how AI-generated a piece of prose reads, in Japanese or English.

    359 GitHub stars~3.6k tokensUpdated 7 days ago
    Business, Finance & HRAuto-check passed
  • AI Slop Cleaner

    yangyuan-zhen/PolyWeather

    [OMX] Run an anti-slop cleanup/refactor/deslop workflow. An agent skill from yangyuan-zhen/PolyWeather.

    316 GitHub stars~2.2k tokensUpdated 19 days ago
    Writing & ContentAuto-check passed

More from irfndi/prism-liquidity-agent

  • Prism

    irfndi/prism-liquidity-agent

    Operate Prism, an autonomous Solana DLMM liquidity agent for Meteora pools.

    123 GitHub stars~1.5k tokensUpdated 11 days ago
    Auto-check passed
  • Prism Openclaw

    irfndi/prism-liquidity-agent

    Operate Prism, an autonomous Solana DLMM liquidity agent for Meteora pools, through the OpenClaw Gateway.

    123 GitHub stars~791 tokensUpdated 11 days ago
    Auto-check passed
  • Prism Hermes

    irfndi/prism-liquidity-agent

    Operate Prism, an autonomous Solana DLMM liquidity agent for Meteora pools, through Hermes ACP.

    123 GitHub stars~807 tokensUpdated 11 days ago
    Auto-check passed

Questions about Prism Maintain

What does Prism Maintain do?

Maintain the Prism codebase: measure cyclomatic complexity, refactor hotspots, and enforce the anti-slop type discipline. Prism Maintain is an agent skill from irfndi/prism-liquidity-agent. Maintain the Prism codebase: measure cyclomatic complexity, refactor hotspots, and enforce the anti-slop type discipline.

When should I use Prism Maintain?

Prism Maintain fits situations like: the user asks about complexity; maintainability; clean up the Prism repo.

How do I install Prism Maintain in Claude Code?

Run `npx skills add irfndi/prism-liquidity-agent --skill prism-maintain -a claude-code`. Or copy the skill folder (skills/prism-maintain in irfndi/prism-liquidity-agent) into .claude/skills/prism-maintain in your project. Claude Code loads it when a task matches its description.

How do I install Prism Maintain in Codex?

Run `npx skills add irfndi/prism-liquidity-agent --skill prism-maintain -a codex`. Or copy the skill folder (skills/prism-maintain in irfndi/prism-liquidity-agent) into .agents/skills/prism-maintain in your project. Codex loads it when a task matches its description.

Can I use Prism Maintain in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add irfndi/prism-liquidity-agent --skill prism-maintain -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/prism-maintain, .gemini/skills/prism-maintain, .github/skills/prism-maintain and .opencode/skills/prism-maintain in your project.

What does Prism Maintain need to run?

Going by SKILL.md and its folder, Prism Maintain needs the command-line tools its instructions call (bun and bunx). Compatibility (from SKILL.md): Requires Bun 1.4+ and oxlint with the vendored anti-slop plugin..

Does Prism Maintain access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Prism Maintain safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Prism Maintain use?

Prism Maintain is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Prism Maintain use?

About 1k tokens (SKILL.md is roughly 4.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Prism Maintain?

Skills that share tags, products or a category with Prism Maintain: Code Quality Gate (fengshao1227/ccg-workflow, 5.9k stars), Deslop (MrZoyo/deslop-GPT, 137 stars), Deslop (sanity-io/sanity, 6.4k stars) and Uncle Bob Craft (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Prism Maintain?

irfndi (a GitHub user) maintains it in irfndi/prism-liquidity-agent, which has 123 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on September 28, 2026.

Source: irfndi/prism-liquidity-agent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.