agentmods.dev

alignment-monitor

alignment-monitor is an agent for Claude Code from Zeekeey-jpeg/LeRoy-HQ. It costs 99 tokens per session (3,406 once invoked), scanned A, original, MIT.

An agent that checks whether an organization’s skills and agents are correctly connected. It looks for skills missing from index files, links to deleted files, weak keyword routing, and test files that should be archived.

In plain words
What is it for?
Use it for system health checks, after adding skills or agents, and during scheduled maintenance. It can detect orphaned skills, dead references, routing gaps, and unnecessary skill files.
Why use it?
It catches gaps that can make an available skill impossible to find or send a request to the wrong workflow. Regular checks also help prevent unused or outdated resources from accumulating.

Agent for Claude Code

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

not rated 10repo 19d ago A scan 99 tokens original MIT

Good fit Use it for system health checks, after adding skills or agents, and during scheduled maintenance. It can detect orphaned skills, dead references, routing gaps, and unnecessary skill files.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/zeekeey-jpeg/leroy-hq/alignment-monitor
View source ↗ Zeekeey-jpeg/LeRoy-HQ
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/Zeekeey-jpeg/LeRoy-HQ

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 alignment-monitor

README.md
[![agentmods](https://agentmods.dev/badge/agents/zeekeey-jpeg/leroy-hq/alignment-monitor/github.svg)](https://agentmods.dev/agents/zeekeey-jpeg/leroy-hq/alignment-monitor)
Your own site
<a href="https://agentmods.dev/agents/zeekeey-jpeg/leroy-hq/alignment-monitor"><img src="https://agentmods.dev/badge/agents/zeekeey-jpeg/leroy-hq/alignment-monitor/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 alignment-monitor

Your own site · 80×15
<a href="https://agentmods.dev/agents/zeekeey-jpeg/leroy-hq/alignment-monitor"><img src="https://agentmods.dev/badge/agents/zeekeey-jpeg/leroy-hq/alignment-monitor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 99 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,406 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00099 $0.03406
Opus 5 $0.00049 $0.01703
Sonnet 5 $0.00020 $0.00681
Haiku 4.5 $0.00010 $0.00341

Measured 12d ago against content hash ac33af4c1a46, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

alignment-monitor 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 12d 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.

core/agents/alignment-monitor.md · 337 lines

How it starts

The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Alignment Monitor Agent

Tier: 5 (Support & Background) Reports To: CKO (Chief Knowledge Officer) Model: haiku Color: orange Auto-Spawn: Weekly (Monday cleanup) + on skill/agent creation

Role

Maintain 97%+ skill-agent alignment by detecting orphans, dead references, and routing gaps before they accumulate.

System Prompt

You are the alignment monitor agent. Your job is to ensure every skill file in the skills/ directory is properly referenced in its parent index.md file, and that no index files contain dead references to deleted files.

Core Responsibilities

  1. Orphan Detection - Find skill .md files not referenced in any index

  2. Dead Reference Detection - Find index entries pointing to nonexistent files

  3. Routing Gap Analysis - Ensure keyword coverage is adequate per skill

  4. Archive Enforcement - Flag test/stub files for archival

  5. New Skill Validation - When a skill is created, verify it gets indexed

  6. Harness Bloat Scan (added 2026-07-23) - Beyond "is it reachable?", ask "does it earn its place?". Protocol: skills/meta/minimalism-audit.md. Four dimensions:

    • Never-loaded skills — reachable but never actually loaded. Cross-reference scripts/skill-usage-tracker.py output and session/agent-last-used.json; flag anything unloaded for 90+ days.
    • Overlapping-content clusters — two or more skills with substantially duplicate triggers or content. These split routing so neither reliably wins.
    • Stale self-reported inventories — a file claiming counts that no longer match reality. Known case: skills/meta/skill-shopping.md claims "32 skills" while skills/meta/ alone holds ~95.
    • Superseded siblings — .bak, .broken, -v2, .py.bak-* next to live files.

    Report-only. Never delete; archive per the existing Archive Protocol. Findings that represent deliberate deferrals go to session/debt-ledger.jsonl.

Scan Protocol (v2 — cross-domain aware)

Read the full file on GitHub · 337 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. 12d ago First seen · 337 lines · 99 tokens per session scan A ac33af4c1a46

Subscribe to this mod's changes

alignment-monitor is an agent published in the GitHub repository Zeekeey-jpeg/LeRoy-HQ (10 stars, last pushed 19d ago), licensed MIT. It adds 99 tokens to every session and 3,406 once invoked, about $0.0005 per session on Opus 5. 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.

Building agentsClaude Codeagent-orchestrationagentic-aiai-agentsclaudemulti-agent-systems
Related

Other agents, from other repositories

sdk-api-documenter

Generate and validate documentation for @a5c-ai/babysitter-sdk CLI commands and exported APIs.

a5c-ai/babysitter · 25 tokens

ux-evaluator

Use this agent for read-only UX evaluation of test-runner driver artifacts (Playwright AX-tree snapshots, screenshots, console output). Applies the 4-check UX rubric (onboarding-step-count ≤7, axe-violations critical/serious, console-errors visible to user, Apple-Liquid-Glass .glassEffect() conformance on SwiftUI 26+)…

Kanevry/session-orchestrator · 199 tokens

db-specialist

Use this agent for database work — schema design, migrations, queries, indexes, and database functions. Handles SQL, ORMs, and database architecture decisions. Context: New feature requires database schema changes. user: "Create the migration for the invoice tables with proper indexes" assistant: "I'll dispatch the…

Kanevry/session-orchestrator · 166 tokens

eval-judge

Use this agent during the /eval Skill Phase 3 (Epic #803, issue #810) to judge — from a session-eval record's dimension evidence, kpis, and sessionid — the record's instruction-adherence and report-quality per rubric-v1.md's Judge Dimensions section. Dispatched read-only, coordinator-side (never inside a wave) by…

Kanevry/session-orchestrator · 249 tokens

project-discovery

Use this agent when you need to audit project state, map affected modules, or verify assumptions before implementation. Context: Before adding a new feature, the coordinator needs to understand existing code paths. user: "Audit the auth flow" assistant: "I'll use the project-discovery agent to map auth modules and…

Kanevry/session-orchestrator · 0 tokens

rn-pr-qa

Device-tests a GitHub pull request on iOS simulator, Android emulator, and/or a physical device using rn-dev-agent. Installs the PR head, exercises the change, and reports pass/fail with repro steps and screenshots/logs. PARENT-SESSION-ONLY: requires MCP tools (cdp, device, rnsession) — do NOT spawn via Task tool, run…

Lykhoyda/rn-dev-agent · 299 tokens