Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add iamcxa/kc-claude-plugins/plugin install kc-plugin-forgeWrote 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/skills/iamcxa/kc-claude-plugins/kc-plugin-forge-sanitize-check)<a href="https://agentmods.dev/skills/iamcxa/kc-claude-plugins/kc-plugin-forge-sanitize-check"><img src="https://agentmods.dev/badge/skills/iamcxa/kc-claude-plugins/kc-plugin-forge-sanitize-check/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/skills/iamcxa/kc-claude-plugins/kc-plugin-forge-sanitize-check"><img src="https://agentmods.dev/badge/skills/iamcxa/kc-claude-plugins/kc-plugin-forge-sanitize-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00090 | $0.01810 |
| Opus 5 | $0.00045 | $0.00905 |
| Sonnet 5 | $0.00018 | $0.00362 |
| Haiku 4.5 | $0.00009 | $0.00181 |
Grade A, and why
kc-plugin-forge-sanitize-check 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin Sanitize-Check
Prepublish backstop. Greps a plugin's public files (reference/*.md, skills/**/*.md, agents/**/*.md, README.md, CLAUDE.md, docs/*.md, skill-scenarios/*.yaml) for known leak patterns. If any hit, block publish with a per-finding report so user can decide: fix, allowlist, or override.
Position in the knowledge ladder: this skill is the safety net AFTER Early-stage Dreaming. Early-stage Dreaming is the primary defense (sanitize at capture time). Sanitize-check exists only because Dreaming is human-gated and humans miss things.
When to invoke
| Trigger | Action |
|---|---|
| Before making a public plugin feature PR ready | Run sanitize-check first; do not proceed if findings exist and the user does not override |
| Before opening a PR to a public plugin repo | Run sanitize-check on the changed files |
| After bulk Dreaming session | Sanity check that distilled rules don't still contain identifiers |
| Periodically (nightwatch) | Audit accumulated drift |
Usage
/kc-plugin-forge sanitize-check <plugin-name>
/kc-plugin-forge sanitize-check <plugin-name> --strict # treat WARN as block
/kc-plugin-forge sanitize-check --all # scan all kc-* plugins
Detection rules
Three rule classes, all configurable in ~/.claude/kc-plugins-config/sanitize-rules.yaml (created on first run with defaults).
Class 1 — BLOCK (literal high-signal identifiers)
Strings that should NEVER appear in public files. Match = block publish.
Default seeds (user adds their own orgs):
DataRecce@recce/(org-scoped npm package)reccehq.combw.tw(real domain)pwd123(known seed credential)[email protected]
User override: edit sanitize-rules.yaml block_literals: list.
Class 2 — WARN (heuristic patterns)
Regex patterns that are usually but not always identifiers. Match = warn, do not block.
Defaults (hardcoded — yaml has disable_warn: list to suppress):
[A-Z]{2,5}-\d{2,6}(likely Linear/Jira ticket) — allowDRC-XXXX,PROJ-NNNtemplates[a-z][-a-z0-9]+/[a-z][-a-z0-9]+#\d+(likely GitHub PR ref)`[0-9a-f]{7,40}`(likely short SHA in markdown code-tick)/Users/[^/]+/(Project|Code|Work)/(likely local path)[A-Za-z0-9._%+-]+@(?!example\.com|test\.com|seed\.[a-z]+)[A-Za-z0-9.-]+\.[A-Za-z]{2,}(likely real email)(feature|fix|chore)/[a-z]{2,5}-\d+(likely ticket-prefixed branch)
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.
- 4d ago Changed · +1 lines b9f9aef03e82
- 9d ago First seen · 165 lines · 90 tokens per session scan A 97901aadd25a
kc-plugin-forge-sanitize-check is a skill published in the GitHub repository iamcxa/kc-claude-plugins (3 stars, last pushed today), licensed MIT. It adds 90 tokens to every session and 1,810 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…