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.
/plugin marketplace add Lander-Parren/sparnpx agentmods add plugins/lander-parren/spar/marketplacegit clone --depth 1 https://github.com/Lander-Parren/sparGrade 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.
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"
]
}
]
}
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.
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.
- yesterday First seen · 41 lines scan A f7ab1c9efc56
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.
Other plugins, from other repositories
pop-quiz
Surprise pop quiz skill: the agent overhoort you on the code it just wrote.
pop-quiz
A surprise pop quiz for developers: after the agent implements something for you, it springs an oral exam on the concepts, terms, and design tradeoffs of the work — so you actually understand what was built and why, and make better decisions next time.
humanizer
Install Humanizer as a Claude plugin.
ainb-hooks
Emit every safely observable Claude Code lifecycle event into Hangar's durable provider log. User-facing events still reach ainb-notifyd over its Unix socket. The same notify.sh powers ATC structured control when installed with AINBMANAGED=atc. stallguard.py additionally blocks turn-end when a session would idle on i.
draft-plugins
Plugin marketplace listing 1 plugin: draft.
google-search-console-mcp
Plugin marketplace listing 1 plugin: google-search-console-mcp.