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.
git clone --depth 1 https://github.com/skymanbp/CodeEraserWrote 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.
[](https://agentmods.dev/plugins/skymanbp/codeeraser/plugin)<a href="https://agentmods.dev/plugins/skymanbp/codeeraser/plugin"><img src="https://agentmods.dev/badge/plugins/skymanbp/codeeraser/plugin/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.
<a href="https://agentmods.dev/plugins/skymanbp/codeeraser/plugin"><img src="https://agentmods.dev/badge/plugins/skymanbp/codeeraser/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade 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 today.
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 (with the tombstone and flow legs judged in the core), records at PostToolUse whether an asked write ran (settle), 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": "1.9.2",
"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 it installs
The manifest is a name and a version. 1 skill, 1 command, 4 hooks, 1 MCP server travel with it, and installing the plugin installs all of them — 71 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- today Changed 18cf0778ba44
- yesterday Changed 8d08cb6fe958
- 2d ago Changed 77f511149c09
- 16d ago Changed e3eda5e4328d
- 26d ago Changed 5c8df147713d
- 1mo ago Changed 88a2871952f0
- 1mo ago Changed 571d2402f6dc
- 1mo ago Changed 88b9dc9e25db
- 1mo ago Changed 996c8001caa5
- 1mo ago First seen · 20 lines scan A e46b7b2e431e
codeeraser is a plugin published in the GitHub repository skymanbp/CodeEraser (21 stars, last pushed today), 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
antidote
Stop AI agents from patching symptoms. Forces structural root-cause fixes over symptom patching in any language or stack.
polygraph
A polygraph for your state machine. The agent does the hard part for you: it instruments your code, builds any test doubles needed to run it, and captures real execution traces — then has an LLM derive a transition-function spec from the source (default: a SAM v2 strict-profile module with named…
falsegreen-skill
Detect false-positive tests (tests that pass even when the code breaks) with the J1-J6 judgment framework. Covers Python, TypeScript, JavaScript, and Robot Framework.
code-analysis
Codebase analysis commands: query, select-files, and file-tree for exploring and understanding repositories.
raysense
Architectural telemetry for AI coding agents. Phase-scoped skills + slash commands over the raysense MCP server: scan + baseline at session start, blast-radius before edits, regression diff after, on-demand architecture audits, time-window drift detection.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.