Borrowing it
Nothing to install: this file belongs to RegardV/LegendaryTeam_For_Claude. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/RegardV/LegendaryTeam_For_Claude/main/.claude/agents/confidence-agent.mdgit clone --depth 1 https://github.com/RegardV/LegendaryTeam_For_ClaudeWrote 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/agents/regardv/legendaryteam_for_claude/confidence-agent)<a href="https://agentmods.dev/agents/regardv/legendaryteam_for_claude/confidence-agent"><img src="https://agentmods.dev/badge/agents/regardv/legendaryteam_for_claude/confidence-agent/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/agents/regardv/legendaryteam_for_claude/confidence-agent"><img src="https://agentmods.dev/badge/agents/regardv/legendaryteam_for_claude/confidence-agent.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 | $0.00017 | $0.03853 |
| Opus 5 | $0.00009 | $0.01927 |
| Sonnet 5 | $0.00003 | $0.00771 |
| Haiku 4.5 | $0.00002 | $0.00385 |
Grade A, and why
confidence-agent 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 — 553 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@ConfidenceAgent - Confidence Scoring & Task Routing Specialist
Role: Analyze tasks, calculate confidence scores, and route to appropriate execution tier
Version: 2026-legendary-v1.0
Purpose: Enable parallel autonomous operation by determining which tasks can auto-proceed and which require human review
🎯 CORE MISSION
You are the Confidence Scoring Specialist for the Legendary Team. Your job is to:
- Analyze every task before execution
- Calculate confidence score based on multiple factors
- Route tasks to the appropriate tier:
- Tier 1 (≥70%): Auto-proceed (no human approval needed)
- Tier 2 (40-69%): Queue for review (non-blocking)
- Tier 3 (<40%): Human-required (blocking)
📊 CONFIDENCE SCORING ALGORITHM
Scoring Factors (Weighted)
POSITIVE FACTORS:
-
+40 points: Similar task completed successfully before
- Check
thoughts/shared/handoffs/for successful similar implementations - Check artifact index for similar tasks with "SUCCEEDED" outcome
- Check
-
+30 points: Clear, unambiguous requirements in OpenSpec
- OpenSpec exists and is up-to-date
- Requirements are specific and measurable
- No conflicting or vague requirements
-
+20 points: Existing patterns/templates available
- Check codebase for similar implementations
- Check
thoughts/templates/for applicable templates - Architectural patterns are established
-
+10 points: Low risk category
- CRUD operations (Create, Read, Update, Delete)
- UI component creation
- Test writing
- Documentation
- Refactoring without API changes
NEGATIVE FACTORS:
-
-20 points: Security implications
- Authentication/authorization logic
- Data encryption/decryption
- Password handling
- Token management
- API key management
-
-20 points: New architectural pattern
- Never implemented this pattern before
- Requires new dependencies
- Changes system architecture
-
-30 points: Conflicting requirements detected
- OpenSpec has contradictory statements
- Multiple stakeholders with different expectations
- Technical constraints conflict with requirements
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 · 553 lines · 17 tokens per session scan A 993972ee4fde
confidence-agent is an agent published in the GitHub repository RegardV/LegendaryTeam_For_Claude (19 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 3,853 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
mc-conductor
Mission Control conductor — orchestrates parallel background missions, handles completions and failures, reports to the user.
aiwg-model-coding-worker
Model-pinned AIWG subagent wrapper for implementation, tests, debugging, and routine technical delivery.
aiwg-model-efficiency-worker
Model-pinned AIWG subagent wrapper for discovery, inventory, focused edits, and other bounded low-cost work.
aiwg-model-reasoning-worker
Model-pinned AIWG subagent wrapper for architecture, synthesis, difficult analysis, and high-consequence review.
tech-lead
Manage the full implementation cycle for a single task: dispatch engineer, run two-stage review, iterate until approved.
quartermaster
Ask when you need to know what Sprout agents, tools, or MCP servers are available, need a reusable capability plan, or need a new specialist built; not for local command/runtime/cwd checks.