observer

A Claude Code plugin for observing file changes and coaching an implementation through selected roles. It also checks individual implementation checkpoints against a specified requirement.

In plain words
What is it for?
Use it to observe coding changes as they happen, act as a rubber duck, pair programmer, or interviewer, and verify a requirement at a checkpoint.
Why use it?
It provides feedback while work is being written and can flag a checkpoint that does not meet its requirement. Its description does not specify how the coaching roles or checks are configured beyond a roles file.

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 NVZver/claude-marketplace
agentmods
npx agentmods add plugins/nvzver/claude-marketplace/observer
Clone the repo
git clone --depth 1 https://github.com/NVZver/claude-marketplace

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

observer 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 2d ago.

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.

observer/.claude-plugin/plugin.json · 12 lines

What it actually says

{
  "name": "observer",
  "description": "Live observe-and-coach discipline for the NVZver marketplace. Rides Claude Code's self-paced /loop through two Actors. observer:observe reacts to your file changes through a chosen role (rubber-duck, pair-programmer, interviewer, custom), read as data from one Knowledge file (roles.md). observer:verify-checkpoint gates an implementer's increment: on a checkpoint signal it grades that one F-requirement does·only (not the whole-plan all check — that stays with lsa:reconcile) and emits CLEAR (auto-clears) or BLOCK (surfaced to the human), read-only to the graded artifacts. Depends on core (ground-rules, output).",
  "version": "0.3.3",
  "author": {
    "name": "Nikita Zverev"
  },
  "dependencies": [
    "core"
  ]
}
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. 2d ago First seen · 12 lines scan A 2053041c25dc

Subscribe to this mod's changes

observer is a plugin published in the GitHub repository NVZver/claude-marketplace (1 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.