agentmods.dev

kc-nightwatch

kc-nightwatch is a skill for Claude Code from iamcxa/kc-claude-plugins. It costs 38 tokens per session (13,159 once invoked), scanned A, original, MIT.

A scheduled workflow that checks monitored plugins for structural problems and improvement signals, then fixes or proposes changes.

In plain words
What is it for?
It validates plugin setup, searches configured feedback sources, compares findings with each plugin's goals, applies eligible quick fixes, and creates improvement proposals.
Why use it?
It turns recurring plugin maintenance into a regular process and uses safety checks before making changes.

Skill for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: reads .claude/ paths.

Part of the kc-nightwatch plugin — 3 skills, 4 agents shipped together

not rated 3repo today A scan 38 tokens original MIT

Good fit It validates plugin setup, searches configured feedback sources, compares findings with each plugin's goals, applies eligible quick fixes, and creates improvement proposals.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/iamcxa/kc-claude-plugins/kc-nightwatch
View source ↗ iamcxa/kc-claude-plugins
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.

Any agent
npx skills add iamcxa/kc-claude-plugins --skill kc-nightwatch
Clone the repo
git clone --depth 1 https://github.com/iamcxa/kc-claude-plugins

Made for: Claude Code.

Or install kc-nightwatch, the plugin that ships this one along with the rest of its 3 skills, 4 agents.

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 kc-nightwatch

README.md
[![agentmods](https://agentmods.dev/badge/skills/iamcxa/kc-claude-plugins/kc-nightwatch/github.svg)](https://agentmods.dev/skills/iamcxa/kc-claude-plugins/kc-nightwatch)
Your own site
<a href="https://agentmods.dev/skills/iamcxa/kc-claude-plugins/kc-nightwatch"><img src="https://agentmods.dev/badge/skills/iamcxa/kc-claude-plugins/kc-nightwatch/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 kc-nightwatch

Your own site · 80×15
<a href="https://agentmods.dev/skills/iamcxa/kc-claude-plugins/kc-nightwatch"><img src="https://agentmods.dev/badge/skills/iamcxa/kc-claude-plugins/kc-nightwatch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 13,159 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 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 $0.00038 $0.13159
Opus 5 $0.00019 $0.06580
Sonnet 5 $0.00008 $0.02632
Haiku 4.5 $0.00004 $0.01316

Measured 9d ago against content hash 6405e8ed4329, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

kc-nightwatch scanned grade A 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -X POST "$WEBHOOK_URL" \
kc-nightwatch/skills/kc-nightwatch/SKILL.md · 1,229 lines

How it starts

The opening of the file, as written. The whole thing — 1,229 lines — stays where its author put it; the contents beside it link to each section on GitHub.

kc-nightwatch — Nightly Plugin Improvement

Autonomous nightly pipeline that patrols each plugin, fixes structural issues, and proposes north-star-aligned improvements.

Core philosophy: Find cracks in the wall and patch them nightly. Never tear down a wall.

Arguments

Parse the invocation arguments:

  • /kc-nightwatch — production mode (all safety guards active)
  • /kc-nightwatch --self-repair — self-repair mode: validate config, collect feedback, check own forge status. Runs as Phase SR (before Phase 0). Does NOT run the regular pipeline.
  • /kc-nightwatch --dry-run — dry-run mode: bypasses skip_if_dirty and skip_if_recent_human_commit guards. Combinable with any mode.

When --dry-run is active, prefix all log output with [DRY-RUN]. When --self-repair is active, prefix all log output with [SELF-REPAIR].

Mode routing:

  • --self-repair → execute Phase SR only, then stop
  • no args / --dry-run only → execute Phase 0-5 (existing pipeline)

Prerequisites Check

Before starting, check for optional plugin dependencies:

  • kc-plugin-forge — invoke Skill: "kc-plugin-forge" with validate-only (used in Phase 1)

If kc-plugin-forge is not loaded:

[WARN] kc-plugin-forge not loaded — Phase 1 (forge validation) will be skipped

Set forge_available = false and continue. Phase 1 will be skipped entirely.

Phase SR: Self-Repair (--self-repair mode only)

Runs in a dedicated session before the regular pipeline. Three responsibilities:

  1. Config validation + auto-fix
  2. Feedback collection from previous runs
  3. Own plugin forge check

Step SR.1: Load Self-Repair Config

Read:

  1. ~/.claude/kc-plugins-config/nightwatch-targets.yaml — targets to validate
  2. config/safety.yaml → self_repair section — limits and matching algorithm
  3. ~/.claude/kc-plugins-config/nightwatch-improvement-log.md → last_run timestamp (for feedback scan window)

Step SR.2: Config Validation + Auto-Fix

For each target in nightwatch-targets.yaml:

Read the full file on GitHub · 1,229 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 · 1,229 lines · 38 tokens per session scan A 6405e8ed4329

Subscribe to this mod's changes

kc-nightwatch is a skill published in the GitHub repository iamcxa/kc-claude-plugins (3 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 13,159 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens