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/dcostenco/prism-coderWrote 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/dcostenco/prism-coder/prism)<a href="https://agentmods.dev/plugins/dcostenco/prism-coder/prism"><img src="https://agentmods.dev/badge/plugins/dcostenco/prism-coder/prism/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/dcostenco/prism-coder/prism"><img src="https://agentmods.dev/badge/plugins/dcostenco/prism-coder/prism.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
prism-coder 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": "prism-coder",
"description": "Your coding agent forgets everything between sessions. Prism gives it a memory that sticks: your decisions, open TODOs, and changed files, restored the moment you return. It goes past a notes store — associative recall surfaces related past work, drift detection catches a long session wandering off-goal, and an on-device model reasons over all of it. Local-only by default: your work and the model reading it never leave your machine.",
"version": "20.21.26",
"author": {
"name": "Synalux",
"email": "[email protected]"
},
"homepage": "https://synalux.ai",
"repository": "https://github.com/dcostenco/prism-coder",
"license": "Apache-2.0",
"keywords": [
"memory",
"local-first",
"local-inference",
"on-device",
"drift-detection",
"knowledge-graph",
"offline",
"privacy",
"mcp"
]
}
What it installs
The manifest is a name and a version. 1 skill, 1 MCP server travel with it, and installing the plugin installs all of them — 52 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 91f7e3391902
- 3d ago Changed 69d7164f0dca
- 4d ago Changed be414b8504e2
- 5d ago Changed 3758953d305e
- 6d ago Changed 9ae1be40280c
- 7d ago Changed f9e6fc2ac9f2
- 12d ago Changed b450ec0c8404
- 16d ago Changed 03f2a08a26d5
- 18d ago Changed 961ce88e3020
- 20d ago First seen · 24 lines scan A 909f0c3e46ef
prism-coder is a plugin published in the GitHub repository dcostenco/prism-coder (158 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
openclaw
OpenClaw AI assistant integration. Chat, manage sessions, access memory, and run async tasks through your OpenClaw instance.
inspeximus
Self-correcting memory for Claude Code. Facts you correct stay corrected, deletions leave a signed receipt you can verify offline, and storing something never calls a model. Also ships the checks: erasureresidue asks whether the bytes actually went — on any store, not just this one.
mcptoon
Zero-dependency CLI for MCP tools and agent skills: compact manifests, TOON-compressed results, and one synced config for every agent; doubles as a single stdio bridge.
hypermnesia-mcp
Cortex — persistent memory for Claude Code that remembers across sessions automatically. Install and forget. Scientific retrieval backed by 97 published references. (Renamed from the 'cortex' plugin to match the PyPI/MCP-registry identity.).
ntfy-mcp-server
Send, manage, and replay ntfy push notifications via MCP. STDIO or Streamable HTTP.
plonk
Use the Plonk macOS toolbox from Claude Code. Needs the app installed: brew install --cask ostapondo/plonk/plonk.