clj-kondo-3color

clj-kondo-3color is a skill for Claude Code from plurigrid/asi. It costs 35 tokens per session (1,931 once invoked), scanned A, original, MIT.

A configuration and workflow for clj-kondo, a static analyzer and linter for Clojure, with diagnostics assigned deterministic colors.

In plain words
What is it for?
Use it to configure Clojure lint rules, map diagnostic levels to colors, and add safety hooks.
Why use it?
It makes lint results easier to classify and provides repeatable visual feedback during parallel linting.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the topos-skills plugin — 29 skills shipped together

Good fit Use it to configure Clojure lint rules, map diagnostic levels to colors, and add safety hooks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/plurigrid/asi/clj-kondo-3color
Install

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.

Any agent
npx skills add plurigrid/asi --skill clj-kondo-3color
Clone the repo
git clone --depth 1 https://github.com/plurigrid/asi

Made for: Claude Code.

Or install topos-skills, the plugin that ships this one along with the rest of its 29 skills.

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 clj-kondo-3color

README.md
[![agentmods](https://agentmods.dev/badge/skills/plurigrid/asi/clj-kondo-3color/github.svg)](https://agentmods.dev/skills/plurigrid/asi/clj-kondo-3color)
Your own site
<a href="https://agentmods.dev/skills/plurigrid/asi/clj-kondo-3color"><img src="https://agentmods.dev/badge/skills/plurigrid/asi/clj-kondo-3color/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 clj-kondo-3color

Your own site · 80×15
<a href="https://agentmods.dev/skills/plurigrid/asi/clj-kondo-3color"><img src="https://agentmods.dev/badge/skills/plurigrid/asi/clj-kondo-3color.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,931 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00035 $0.01931
Opus 5 $0.00017 $0.00966
Sonnet 5 $0.00007 $0.00386
Haiku 4.5 $0.00003 $0.00193

Measured 10d ago against content hash 7d337ba8b562, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

clj-kondo-3color 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 10d 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.

ies/music-topos/.claude-marketplaces/topos-skills/plugins/topos-skills/skills/clj-kondo-3color/SKILL.md · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.

clj-kondo 3-Color Integration

"A linter for Clojure code that sparks joy — now with deterministic color-coded diagnostics."

Overview

clj-kondo is a static analyzer and linter for Clojure. This skill integrates Gay.jl's 3-color streams for:

  1. Diagnostic classification via GF(3) trit assignment
  2. Parallel linting with SPI-compliant color forking
  3. Visual feedback with deterministic color palettes
  4. Plurigrid/ASI alignment for safety-aware linting

Diagnostic Trit Mapping

Trit Level Color Range clj-kondo Level
-1 MINUS Cold (blue) :error
0 ERGODIC Neutral (green) :warning
+1 PLUS Warm (red) :info

GF(3) Conservation: For any 3 consecutive diagnostics:

trit(d₁) + trit(d₂) + trit(d₃) ≡ 0 (mod 3)

Configuration

.clj-kondo/config.edn

{:linters
 {:unresolved-symbol {:level :error}
  :unused-binding {:level :warning}
  :type-mismatch {:level :error}}
 
 ;; Gay.jl color integration
 :gay-colors
 {:enabled true
  :seed 0x42D
  :trit-mapping {:error -1, :warning 0, :info 1}
  :conservation :strict}}

Plurigrid/ASI Safety Hooks

;; .clj-kondo/hooks/gay_safety.clj
(ns hooks.gay-safety
  (:require [clj-kondo.hooks-api :as api]))

(defn check-gf3-conservation
  "Verify GF(3) conservation across findings."
  [{:keys [findings]}]
  (let [trits (map #(case (:level %)
                      :error -1
                      :warning 0
                      :info 1) findings)
        sum (reduce + 0 trits)]
    (when-not (zero? (mod sum 3))
      (api/reg-finding!
       {:message "GF(3) conservation violated"
        :type :gay-conservation
        :level :warning}))))

Integration with SplitMixTernary

(ns music-topos.clj-kondo-gay
  (:require [clj-kondo.core :as clj-kondo]))

(def GOLDEN 0x9E3779B97F4A7C15)
(def MIX1 0xBF58476D1CE4E5B9)
(def MIX2 0x94D049BB133111EB)
(def MASK64 0xFFFFFFFFFFFFFFFF)

(defn splitmix64 [state]
  (let [s (bit-and (+ state GOLDEN) MASK64)
        z (bit-and (* (bit-xor s (unsigned-bit-shift-right s 30)) MIX1) MASK64)
        z (bit-and (* (bit-xor z (unsigned-bit-shift-right z 27)) MIX2) MASK64)]
    {:state s :value (bit-xor z (unsigned-bit-shift-right z 31))}))

(defn color-at [seed idx]
  (loop [s seed i idx]
    (if (zero? i)
      (let [{:keys [value]} (splitmix64 s)]
        {:L (+ 10 (* 85 (/ (double (bit-and value 0xff)) 255)))
         :C (* 100 (/ (double (bit-and (unsigned-bit-shift-right value 8) 0xff)) 255))
         :H (* 360 (/ (double (bit-and (unsigned-bit-shift-right value 16) 0xffff)) 65535))})
      (recur (:state (splitmix64 s)) (dec i)))))

(defn color-finding [seed finding idx]
  (let [color (color-at seed idx)
        trit (case (:level finding) :error -1 :warning 0 :info 1)]
    (assoc finding
           :gay-color color
           :gay-trit trit
           :gay-hex (lch-to-hex (:L color) (:C color) (:H color)))))

(defn lint-with-colors [paths seed]
  (let [result (clj-kondo/run! {:lint paths})
        findings (:findings result)]
    (assoc result
           :findings (map-indexed (fn [i f] (color-finding seed f i)) findings)
           :gf3-sum (reduce + 0 (map :gay-trit findings)))))

Read the full file on GitHub · 205 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. 10d ago First seen · 205 lines · 35 tokens per session scan A 7d337ba8b562

Subscribe to this mod's changes

clj-kondo-3color is a skill published in the GitHub repository plurigrid/asi (62 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 1,931 once invoked, about $0.0002 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 2026-09-01.

Related

Other skills, from other repositories

dotnet-reverse

A guide for analyzing compiled .NET and C# programs, including managed Windows executables and libraries. Reverse engineering means studying compiled software to understand how it works, and decompiling turns it back into readable approximate source code.

zhaoxuya520/reverse-skill · 144 tokens

check-bin-obj-clash

Detects MSBuild projects with conflicting OutputPath or IntermediateOutputPath. USE FOR: builds failing with 'Cannot create a file when that file already exists', 'The process cannot access the file because it is being used by another process', intermittent build failures that succeed on retry, or missing/overwritten…

dotnet/skills · 160 tokens

dart-run-static-analysis

Execute dart analyze to identify warnings and errors, and use dart fix --apply to automatically resolve mechanical lint issues. Use during development to ensure code quality and before committing changes.

flutter/agent-plugins · 43 tokens

hotpath_init

Configure hotpath profiling in a Rust project. Adds the hotpath dependency with feature-gated setup, instruments main with hotpath::main, functions with measure/measureall, and wraps channels, mutexes, rwlocks, streams, futures, reqwest clients, axum routers and byte-level I/O with hotpath macros. Use when the user…

pawurb/hotpath-rs · 88 tokens

agents-sdk-dotnet-debugging

Use when troubleshooting an agent built with the Microsoft Agents SDK (Microsoft.Agents.Hosting.AspNetCore and related packages) in C# / .NET. Trigger on any of these symptoms: build or C# compile errors, crashes on startup, 401 or auth errors on incoming requests, the bot not responding to messages, appsettings.json…

microsoft/Agents · 136 tokens

golang-error-handling

Idiomatic Golang error handling — creation, wrapping with %w, errors.Is/As, errors.Join, custom error types, sentinel errors, panic/recover, the single handling rule, structured logging with slog, HTTP request logging middleware, and samber/oops for production errors. Built to make logs usable at scale with log…

samber/cc-skills-golang · 144 tokens