Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/skills/haileyok/cc-discord/skills)<a href="https://agentmods.dev/skills/haileyok/cc-discord/skills"><img src="https://agentmods.dev/badge/skills/haileyok/cc-discord/skills/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/haileyok/cc-discord/skills"><img src="https://agentmods.dev/badge/skills/haileyok/cc-discord/skills.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 | $0.00039 | $0.00579 |
| Opus 5 | $0.00019 | $0.00290 |
| Sonnet 5 | $0.00008 | $0.00116 |
| Haiku 4.5 | $0.00004 | $0.00058 |
Grade A, and why
ask-discord 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 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.
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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ask the user via Discord
Use this when you are blocked on a decision and the user is plausibly away from the workstation. The bridge daemon (claude-discord-bridge) posts the question to a Discord thread tied to the current session and waits up to 15 minutes for a reply. The user's reply (or a graceful fallback string on timeout / bridge-down) is returned to you to use as conversation context.
When to use
- You've been working autonomously and hit a fork in the road that materially changes the result.
- The decision is hard to undo (data deletion, schema change, deploy, irreversible refactor).
- A code-only check (test runs, type checks) cannot answer the question.
- You'd otherwise wait or guess for >5 minutes.
When NOT to use
- The answer is in the codebase or git history — read it.
- The decision is trivial / reversible — just pick one and proceed.
- The user is at the keyboard (recent activity in this session) — the normal turn-by-turn dialog is faster.
How to invoke
Run the bridge's CLI script via the Bash tool. Pass your session ID (you received it in the session-start system reminder; the skill explicitly authorizes you to pass it to this script) and the current working directory:
python3 /home/discord/claude-discord-bridge/skills/ask_discord.py \
"<the question>" \
--session-id "<your session id>" \
--cwd "$(pwd)"
The script blocks until the user replies in Discord, the bridge times out, or the bridge is unreachable. It always exits 0 and always writes ONE human-readable line to stdout. Use that line as the user's input to the next step of your reasoning.
Examples of return strings:
yes— straight answer.option B because C— answer with rationale.no reply within 15m; proceeding with best-guess— timeout fallback. Make a reasonable call and continue.bridge daemon is not reachable at http://127.0.0.1:8787; is \claude-discord-bridge serve` running?` — bridge-down. Make a reasonable call and continue. Mention the bridge issue to the user when they return.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 45 lines · 39 tokens per session scan A 660a59575060
ask-discord is a skill published in the GitHub repository haileyok/cc-discord (5 stars, last pushed 17d ago), licensed MIT. It adds 39 tokens to every session and 579 once invoked, about $0.0002 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
open-code-review
Performs AI-powered code review on Git changes using the ocr CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply…
harness-creator
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…
remote-claude-code
Run Claude Code on a remote host over SSH — a persistent expect-driven login session, headless claude -p with the stdin fix, the interactive TUI inside a remote tmux driven by send-keys/capture-pane (one keystroke at a time, capture-verified; relayed user messages go through verbatim), and multi-turn continuity via…
web-design
Penguin visual language for generated web pages and app UIs — GitHub-style simplicity with a single blue accent, light and pure-black dark themes, design tokens, component and chat-interface recipes, plus an opt-in warm paper editorial theme.
agent-optimization
Improve an Agent State through versioned scores and score-linked Traces from a frozen Benchmark.
agent-evaluation
Run one specified Test Agent on one specified Benchmark Case exactly once, privately score that execution, and return one protocol result.