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 skills add zstevovich/claude-apd --skill apd-togglegit clone --depth 1 https://github.com/zstevovich/claude-apdWrote 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/zstevovich/claude-apd/apd-toggle)<a href="https://agentmods.dev/skills/zstevovich/claude-apd/apd-toggle"><img src="https://agentmods.dev/badge/skills/zstevovich/claude-apd/apd-toggle.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 | $0.00127 | $0.01094 |
| Opus 5 | $0.00063 | $0.00547 |
| Sonnet 5 | $0.00025 | $0.00219 |
| Haiku 4.5 | $0.00013 | $0.00109 |
Grade B, and why
apd-toggle 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 8d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
description: Toggle claude-apd@zstevovich-plugins enabled state in CC settings without leaving the session. Use when the user asks to disable APD, turn it off, enable it, switch APD on/off, or hit a guard block they want How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
APD Toggle
Quick switch for the claude-apd plugin's enabledPlugins state in CC settings. CC-only — Codex has no equivalent concept.
When to use
- User asks: "turn off APD", "iskljuci APD", "disable apd", "enable apd", "switch APD off", "ugasi APD u ovoj sesiji", "vrati APD nazad", or any phrasing requesting plugin toggle.
- User wants to do quick non-APD work in a project that has APD enabled, without leaving the session.
- User wants to enable APD in a project where it's currently off.
- User asks "kako da ugasim APD" — answer with this skill, not with manual JSON edit instructions.
When NOT to use
- To get an out-of-scope fix past a cycle cap or a gate mid-pipeline.
toggle offdisables the WHOLE enforcement layer, so the fix lands with no fresh adversarial pass — and it is usually a finding on exactly the paths that most need one. Since v6.29 the toggle refuses this: withAPD_ACTIVEand aspec-card.mdpresent it exits 2 withtoggle-off-active-pipeline. The sanctioned routes, in order:- out of scope →
apd pipeline spinoff-finding <id> "<reason>", then continue in scope - genuinely in scope, out of cycles →
apd pipeline raise-cap builder|reviewer <N> "<reason>" - done with the run →
apd pipeline reset--force "<reason>"exists as a valve for a real emergency and logstoggle-off-forced; reaching for it routinely means the run should have been reset or the finding spun off.
- out of scope →
- User wants to UNINSTALL the plugin entirely (use
/plugin uninstalldirectly — different operation). - User is on Codex — no
enabledPluginsconcept exists, this skill does nothing useful there. - User wants to disable a different plugin (e.g. superpowers) — this skill is APD-specific.
Process
Step 1 — Parse intent
User intent → flag:
| User said | Flag |
|---|---|
| "turn off", "disable", "iskljuci", "ugasi" | off |
| "turn on", "enable", "ukljuci", "vrati" | on |
| "toggle", "flip", "switch", or unspecified | (no arg — flip current state) |
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.
- 8d ago First seen · 85 lines · 127 tokens per session scan B 688fb48555d1
apd-toggle is a skill published in the GitHub repository zstevovich/claude-apd (5 stars, last pushed 1mo ago), licensed MIT. It adds 127 tokens to every session and 1,094 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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-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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…