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.
npx agentmods add skills/iamcxa/kc-claude-plugins/kc-plugin-forge-helpnpx skills add iamcxa/kc-claude-plugins --skill kc-plugin-forge-helpgit clone --depth 1 https://github.com/iamcxa/kc-claude-pluginsWrote 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-help)<a href="https://agentmods.dev/skills/iamcxa/kc-claude-plugins/kc-plugin-forge-help"><img src="https://agentmods.dev/badge/skills/iamcxa/kc-claude-plugins/kc-plugin-forge-help.svg" alt="Measured on agentmods" 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 | $0.00069 | $0.01793 |
| Opus 5 | $0.00034 | $0.00897 |
| Sonnet 5 | $0.00014 | $0.00359 |
| Haiku 4.5 | $0.00007 | $0.00179 |
Grade A, and why
kc-plugin-forge-help 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 5d 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin Forge Help — Interactive Guide
Help users discover, understand, and improve the Plugin Forge pipeline.
Invocation
/kc-plugin-forge-help # Overview of all commands
/kc-plugin-forge-help <topic> # Deep dive into a topic
/kc-plugin-forge-help --feedback "<message>" # Report a doc gap or feature request
/kc-plugin-forge-help --list-topics # Show available help topics
Phase 1 — Parse Args
| Arg | Mode |
|---|---|
(none) or --list-topics |
Overview |
<topic> |
Topic deep dive |
--feedback "<message>" |
Feedback collection |
Phase 2 — Overview Mode (no args)
Present a complete command reference by reading live skill data:
Read → ${CLAUDE_PLUGIN_ROOT}/skills/*/SKILL.md (extract name + description from frontmatter)
Read → ${CLAUDE_PLUGIN_ROOT}/reference/*.md (extract filenames for topic mapping)
Use the template below as a formatting guide only. Populate the Commands table from the live reads above — do not emit hardcoded rows that differ from what the file system contains.
Present:
# Plugin Forge — Quick Reference
## Commands
| Command | What it does |
|---------|-------------|
| `/kc-plugin-forge <path>` | Full pipeline: validate → TDD → agents → report |
| `/kc-plugin-forge new <name>` | Scaffold a new plugin, then full pipeline |
| `/kc-plugin-forge validate-only` | Phase 1 only — structure check |
| `/kc-plugin-forge skill-tdd-only` | Phase 2 only — TDD cycle per skill |
| `/kc-plugin-forge agent-verify-only` | Phase 3 only — verify agent definitions |
| `/kc-plugin-forge self-forge` | Forge audits itself (Phase 2 + 4) |
| `/kc-plugin-forge-help` | This help screen |
## Pipeline Phases
| Phase | What it does |
|-------|-------------|
| 1. Structure | Validate plugin.json, file layout, agent frontmatter |
| 1.5 Autonomy | A: Self-Learning (D1/D2) + B: Doc Self-Iteration |
| 2. Skill TDD | RED/GREEN/REFACTOR cycle per skill |
| 3. Agent Verify | Check examples, tools, prompts per agent |
| 4. Report | Re-validate + summary + learning capture |
## Topics (use `/kc-plugin-forge-help <topic>` for details)
| Topic | Covers |
|-------|--------|
| `getting-started` | Install, prerequisites, first forge run |
| `phases` | Deep dive into Phase 1 → 4 |
| `routes` | All routes explained (full, validate-only, skill-tdd, etc.) |
| `self-improvement` | D1/D2 learning framework, learned-patterns.md |
| `doc-sync` | Template-based doc self-iteration |
| `self-forge` | Running forge on itself |
| `gotchas` | Common pitfalls from quality-pipeline.md |
| `prerequisites` | Required marketplace plugins |
## Quick Start
**First time? Validate an existing plugin:**
1. Install prerequisites: `superpowers` + `plugin-dev` marketplace plugins
2. `/kc-plugin-forge path/to/my-plugin` → runs full 4-phase pipeline
3. Review report → fix any FAIL items
**Creating a new plugin?**
`/kc-plugin-forge new my-plugin` → scaffold + full pipeline
**Just checking structure?**
`/kc-plugin-forge validate-only` → Phase 1 only
**Periodic self-audit?**
`/kc-plugin-forge self-forge` → forge audits its own skill quality
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.
- 5d ago First seen · 193 lines · 69 tokens per session scan A 326ca8dc400e
kc-plugin-forge-help is a skill published in the GitHub repository iamcxa/kc-claude-plugins (3 stars, last pushed today), licensed MIT. It adds 69 tokens to every session and 1,793 once invoked, about $0.0003 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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…