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 skymanbp/CodeErasernpx agentmods add plugins/skymanbp/codeeraser/plugingit clone --depth 1 https://github.com/skymanbp/CodeEraserGrade A, and why
codeeraser 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
{
"name": "codeeraser",
"description": "CodeEraser passive guard + erase skill: a winnowing clone index behind a per-project daemon intercepts T1/T2 duplicate writes at PreToolUse, audits net LOC + touched duplicates at Stop, and reports health at SessionStart; the erase skill walks findings to safe, re-gated deletions. Gradual modes observe/warn/ask/deny via ce.toml [guard]; every event feeds .ce/observe.ndjson. The starter resolves both binaries (ce + the ce-core judgment core) by pin (ADR-007): a copy in the plugin data dir or on PATH whose SHA256 matches plugin/bin/manifest.env answers first — the installer leaves one there — then a pinned download from GitHub Releases, then an unverified PATH binary that says so.",
"version": "1.4.0",
"author": {
"name": "skymanbp"
},
"license": "Apache-2.0",
"homepage": "https://github.com/skymanbp/CodeEraser",
"repository": "https://github.com/skymanbp/CodeEraser",
"keywords": [
"codeeraser",
"deduplication",
"clone-detection",
"code-quality",
"hooks",
"guard"
]
}
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 · 20 lines scan A f1cf356aaff6
codeeraser is a plugin published in the GitHub repository skymanbp/CodeEraser (20 stars, last pushed yesterday), licensed Apache-2.0. 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 2026-08-30.
Other plugins, from other repositories
pyscn-marketplace
Plugin marketplace listing 1 plugin: pyscn-mcp.
pyscn-mcp
Python code quality analysis MCP server.
sentrux-marketplace
Sentrux — live codebase visualization and structural quality gate for AI-agent-written code.
claude-plugin
Live codebase visualization and structural quality gate — 14 health dimensions graded A-F, dependency analysis, and architecture governance via MCP.
purist
A single skill that hardens the style checkers and static analyzers already wired into a project: discovers every configuration in place, raises each tool to its strictest practical setting, and adds a list of custom rules on top — it cranks what is configured rather than introducing a new toolchain.
customgpt-claude-quadruple-verification
Quadruple verification for Claude Code — automatically blocks placeholder code, security vulnerabilities, and ensures output quality on every operation. Built by CustomGPT.ai for production teams.