spar

A coding-agent add-on for learning during software development. It asks you to predict what will happen before implementation, then records differences between your expectations and reality for later practice.

In plain words
What is it for?
Use it to practise coding, review mistakes, and receive explanations while an AI agent works.
Why use it?
It helps reveal gaps in your understanding instead of letting the agent write code without explanation or reflection.

Plugin for Claude Code

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.

Claude Code
/plugin marketplace add Lander-Parren/spar
agentmods
npx agentmods add plugins/lander-parren/spar/marketplace
Clone the repo
git clone --depth 1 https://github.com/Lander-Parren/spar

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

spar 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.

.claude-plugin/marketplace.json · 41 lines

What it actually says

{
  "$schema": "https://json.schemastore.org/claude-code-marketplace-manifest.json",
  "name": "spar",
  "owner": {
    "name": "Lander Parren",
    "url": "https://github.com/Lander-Parren"
  },
  "description": "Keep learning while AI writes the code, plus the writing skill spar leans on when it explains something back to you.",
  "plugins": [
    {
      "name": "spar",
      "source": "./",
      "description": "Predict before the agent implements, then log every gap between your model and reality as a curriculum.",
      "license": "MIT",
      "keywords": [
        "learning",
        "deliberate-practice",
        "code-review",
        "hooks",
        "spaced-repetition"
      ]
    },
    {
      "name": "humanizer",
      "source": {
        "source": "url",
        "url": "https://github.com/blader/humanizer.git",
        "sha": "e2e92e7b4b8229253ed5c8e81dc65463fdeddda5"
      },
      "description": "Remove the tells of AI writing. Optional, and not written by spar: MIT, Copyright (c) 2025 Siqi Chen, https://github.com/blader/humanizer. Listed here because spar spends its whole life explaining things to someone who is still confused, and that writing should not read like a machine produced it.",
      "license": "MIT",
      "keywords": [
        "writing",
        "editing",
        "prose",
        "style"
      ]
    }
  ]
}
Files

What ships with it

1 file beside marketplace.json 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.

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. yesterday First seen · 41 lines scan A f7ab1c9efc56

Subscribe to this mod's changes

spar is a plugin published in the GitHub repository Lander-Parren/spar (0 stars, last pushed 8d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-31.