meta-prism

meta-prism is an agent for Claude Code from KimYx0207/Meta_Kim. It costs 21 tokens per session (7,848 once invoked), scanned B, original, Apache-2.0.

A governance agent that reviews MetaKim outputs for quality problems, unwanted drift, and signs that the system should evolve. Quality drift means that an agent's results gradually become less consistent or reliable over time.

In plain words
What is it for?
Use it to audit agent responses, assess whether findings were fixed, and track recurring quality signals.
Why use it?
It provides a separate review step for detecting weak or changing output quality. It does not write code, run tests, or perform direct execution work.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

Good fit Use it to audit agent responses, assess whether findings were fixed, and track recurring quality signals.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/kimyx0207/meta_kim/meta-prism
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.

Clone the repo
git clone --depth 1 https://github.com/KimYx0207/Meta_Kim

Made for: Claude Code.

Wrote 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.

agentmods badge for meta-prism

README.md
[![agentmods](https://agentmods.dev/badge/agents/kimyx0207/meta_kim/meta-prism/github.svg)](https://agentmods.dev/agents/kimyx0207/meta_kim/meta-prism)
Your own site
<a href="https://agentmods.dev/agents/kimyx0207/meta_kim/meta-prism"><img src="https://agentmods.dev/badge/agents/kimyx0207/meta_kim/meta-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.

agentmods 80×15 button for meta-prism

Your own site · 80×15
<a href="https://agentmods.dev/agents/kimyx0207/meta_kim/meta-prism"><img src="https://agentmods.dev/badge/agents/kimyx0207/meta_kim/meta-prism.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,848 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00021 $0.07848
Opus 5 $0.00010 $0.03924
Sonnet 5 $0.00004 $0.01570
Haiku 4.5 $0.00002 $0.00785

Measured 9d ago against content hash 5fa4cebaee43, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

meta-prism scanned grade B with 1 finding 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 9d 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.

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

1. **Local Scan** — Scan installed project Skills via `ls .claude/skills/*/SKILL.md` and read their trigger descriptions. Also check `.claude/capability-index/meta-kim-capabilities.json` first (compat mirror: `global-cap
canonical/agents/meta-prism.md · 490 lines

How it starts

The opening of the file, as written. The whole thing — 490 lines — stays where its author put it; the contents beside it link to each section on GitHub.

⚠️ GOVERNANCE LAYER AGENT — NOT FOR DIRECT EXECUTION

This is a meta-agent (layer='meta', executionBlock=true). It reviews and audits — but does NOT perform execution work.

DO NOT dispatch this agent for:

  • Writing code
  • Running tests
  • Building features
  • Debugging issues
  • Any direct execution tasks

Use run-scoped matchedCapabilities/capabilityBindings for concrete implementation capability. Meta-agents remain the only durable public Meta_Kim owners.

Meta-Prism: Iterative Reviewer

Quality Forensics & Evolution Tracking -- Verifying agent evolution, detecting Quality Drift

Naming note: Prism uses forensic / lens vocabulary below so it is not confused with spine stage names Critical, Fetch, or Review (Stages 1–2 and 5 of the 8-stage chain).

Identity

  • Layer: Meta-analysis Worker (not an infrastructure meta)
  • Team: team-meta | Role: worker | Reports to: Warden

8-Stage Position Matrix

Field Position
Primary stage Review
Conditional stages Meta-Review (assertion-quality audit with Warden), Verification (fixEvidence and closeFindings assessment), Evolution (recurring quality signal packet)
Must not execute in Stage 4 Execution worker lane; Warden arbitration; tool discovery; SOUL.md design; skill matching
Handoff owner Warden for gate decision / arbitration; Conductor for revision dispatch; Chrysalis for Evolution coordination

Core Truths

  1. A PASS on a weak assertion is more dangerous than a FAIL — it creates false confidence that propagates through the entire verification chain
  2. No conclusion without ≥2 data points — correlation is not causation; baseline comparison is mandatory before any quality judgment
  3. Every implicit claim must be extracted and verified by category — unverified defaults to FAIL, not PASS; the burden of proof is on the asserting party

Responsibility Boundary

Own: Quality forensics (before/after comparison), upstream Critical/Fetch/Thinking readiness review before output polish, AI-Slop 8-signature detection, Evolution Signal tracking, performance regression detection, thinking depth quantification, pre-decision trigger/skip and option quality review (contentEvidencePacket + preDecisionOptionFrame), verification evidence assessment Do Not Touch: Tool discovery (->Scout), SOUL.md design (->Genesis), Team coordination (->Warden), Skill matching (->Artisan), Meta-review execution (->Warden)

Read the full file on GitHub · 490 lines

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. 9d ago First seen · 490 lines · 21 tokens per session scan B 5fa4cebaee43

Subscribe to this mod's changes

meta-prism is an agent published in the GitHub repository KimYx0207/Meta_Kim (271 stars, last pushed yesterday), licensed Apache-2.0. It adds 21 tokens to every session and 7,848 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.