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/ivanlutsenko/awac-ai-agent-plugins/sync-themenpx skills add IvanLutsenko/awac-ai-agent-plugins --skill sync-themegit clone --depth 1 https://github.com/IvanLutsenko/awac-ai-agent-pluginsWhat 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 | $0.00061 | $0.00519 |
| Opus 5 | $0.00030 | $0.00260 |
| Sonnet 5 | $0.00012 | $0.00104 |
| Haiku 4.5 | $0.00006 | $0.00052 |
Grade B, and why
sync-theme scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- Claude Code — `~/.claude/settings.json` `theme` (light → `custom:gruvbox-light`, dark → `custom:sunset-drive`) What it actually says
Auto Theme — manual sync
This plugin keeps editor themes in step with the macOS system appearance
(light/dark). Switching is normally automatic via a UserPromptSubmit hook;
this skill is the on-demand trigger.
Run the bundled script. It detects the macOS appearance and sets both editors:
- Claude Code —
~/.claude/settings.jsontheme(light →custom:gruvbox-light, dark →custom:sunset-drive) - Codex —
~/.codex/config.toml[tui] theme(light →gruvbox-light, dark →sunset-drive)
It also installs the bundled themes on first run (~/.claude/themes/,
~/.codex/themes/) if absent.
Execution & Communication Rules:
- First, check if the host OS is Darwin (macOS). If not, refuse to run and output:
Error: Host environment is not macOS. - Run the bash command. Ensure you capture stderr.
- Run the script and surface any
WARN:lines from stderr exactly as emitted. - Treat
WARN: <path> malformed, skippedandWARN: <path> not writableas script-reported configuration problems; do not invent different error text. - Response Format: Output a 2-line bulleted summary detailing: Line 1: Detected OS appearance, Line 2: The exact themes written to both files. Do not include conversational filler.
bash "${CLAUDE_PLUGIN_ROOT:-${CODEX_PLUGIN_ROOT}}/sync-theme.sh"
Automatic switching (one-time setup)
Codex plugins cannot declare hooks in their manifest, so register the hook once
in ~/.codex/hooks.json (then trust it via ~/.codex/config.toml [hooks.state]):
{
"hooks": {
"UserPromptSubmit": [
{ "hooks": [ { "type": "command", "command": "bash '<plugin-root>/sync-theme.sh'", "timeout": 10 } ] }
]
}
}
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.
- 2d ago First seen · 46 lines · 61 tokens per session scan B 66ef1f21cca7
sync-theme is a skill published in the GitHub repository IvanLutsenko/awac-ai-agent-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 519 once invoked, about $0.0003 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.