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 adilkalam/orca --skill orca-confirmgit clone --depth 1 https://github.com/adilkalam/orcaWrote 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/adilkalam/orca/orca-confirm)<a href="https://agentmods.dev/skills/adilkalam/orca/orca-confirm"><img src="https://agentmods.dev/badge/skills/adilkalam/orca/orca-confirm/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/adilkalam/orca/orca-confirm"><img src="https://agentmods.dev/badge/skills/adilkalam/orca/orca-confirm.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 | $0.00014 | $0.01304 |
| Opus 5.5 | $0.00006 | $0.00522 |
| Sonnet 5.5 | $0.00003 | $0.00261 |
| Haiku 4.5 | $0.00001 | $0.00130 |
Grade A, and why
orca-confirm 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 1mo 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 — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orca Team Confirmation Skill
Purpose: Handle user confirmation for agent team selection with automatic bypass mode detection.
Input: User's request is implicitly available. You receive the proposed team and project type as arguments.
Critical Rules (Read First)
- Ask for confirmation ONCE using AskUserQuestion
- Check response structure immediately after receiving it
- If response.answers is empty → BYPASS MODE → Return immediately
- NEVER retry AskUserQuestion if first attempt returned blank
- Return a structured result that main /orca can parse
Implementation
Step 1: Present Proposed Team (VISIBLE OUTPUT - NOT IN TOOL CALL)
CRITICAL: This must be VISIBLE MARKDOWN OUTPUT, not inside AskUserQuestion.
Output this as regular text so the user can see it:
## Proposed Pipeline
**Request:** [task description]
**Domain:** [PROJECT_TYPE]
**Complexity:** [simple/medium/complex]
### Agent Team
| Role | Agent |
|------|-------|
| Coordination | [grand-architect] |
| Architecture | [architect] |
| Implementation | [builder] |
| Specialists | [list them] |
| Gates | [gate agents] |
| Verification | [verification agent] |
### Files Likely Affected
- [from ContextBundle]
### Risks/Notes
- [any identified]
This output MUST appear BEFORE you call AskUserQuestion.
Step 2: Ask for Confirmation (ONCE ONLY - SIMPLE QUESTION)
Use AskUserQuestion with these exact options:
Question: "Proceed with this team?"
Options:
1. "Yes, proceed" → Proceed with proposed team
2. "Modify team" → Ask user what to change
Step 3: Check Response Structure
Immediately after AskUserQuestion returns, check the response:
# Pseudo-code for what you MUST check:
if response is None or response.get("answers") is None or len(response.get("answers", {})) == 0:
# BYPASS MODE DETECTED
# User has bypass permissions enabled
# They CANNOT respond to questions
# Proceed immediately with proposed team
Output:
" Proceeding with proposed team (bypass mode detected - confirmation unavailable)
Proposed Team: [list team]
You can interrupt if you need changes."
# Return to /orca with: BYPASS|original_team
else:
# INTERACTIVE MODE
# User provided an answer
user_answer = response["answers"][first_question_key]
if user_answer == "Yes, proceed":
Output: " Team confirmed"
# Return to /orca with: CONFIRMED|original_team
elif user_answer == "Modify team":
# Ask user what to change
# Adjust team based on their input
# Return to /orca with: MODIFIED|new_team_list
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.
- 1mo ago First seen · 232 lines · 14 tokens per session scan A eddad6ac09b2
orca-confirm is a skill published in the GitHub repository adilkalam/orca (2 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 1,304 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…