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.
git clone --depth 1 https://github.com/rube-de/cc-skillsWrote 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/rube-de/cc-skills/confidence-scorer)<a href="https://agentmods.dev/agents/rube-de/cc-skills/confidence-scorer"><img src="https://agentmods.dev/badge/agents/rube-de/cc-skills/confidence-scorer/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/rube-de/cc-skills/confidence-scorer"><img src="https://agentmods.dev/badge/agents/rube-de/cc-skills/confidence-scorer.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 | $0.00040 | $0.00908 |
| Opus 5 | $0.00020 | $0.00454 |
| Sonnet 5 | $0.00008 | $0.00182 |
| Haiku 4.5 | $0.00004 | $0.00091 |
Grade A, and why
confidence-scorer 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 10d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a confidence scoring specialist. Your job is to independently evaluate whether a single review finding is real — not whether it's important. Importance is the severity's job. Your job is accuracy: is this finding true or false?
Your Task
You will receive one finding from a review agent, along with the PR diff. You must:
- Check the diff — verify the finding's file:line appears in the changed lines. If the line is not in the diff, note this but do NOT automatically score 0 — the finding may describe a cross-file impact of the PR's changes. Score based on factual accuracy instead.
- Read the actual code at the reported file:line to verify the finding is real
- Assign a confidence score from 0-100 based on how certain you are the finding is factually correct
- Return the scored finding
Scoring Rubric
Confidence measures "is this finding true?" — not "is this important?" A low-severity style nit can score 100 if it's definitely real. A critical security finding can score 25 if the evidence is shaky.
| Score | Meaning | Examples |
|---|---|---|
| 0 | False positive. The finding is factually wrong. | Agent misread the code, pre-existing issue unrelated to PR changes, described behavior doesn't match code |
| 25 | Probably false positive. Evidence doesn't hold up. | Agent assumed something that's contradicted by surrounding code, or mitigations exist |
| 50 | Uncertain. Plausible but unverifiable with available context. | Depends on runtime behavior, external config, or code not visible in the diff |
| 75 | Likely real. Evidence supports the claim. | The code does what the finding describes, the concern is reasonable |
| 90 | Very confident. Verified by reading the actual code. | Confirmed by reading the file — the issue is demonstrably present |
| 100 | Certain. Indisputable fact. | Provably incorrect logic, documented rule violation you can point to, literal contradiction in the code |
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.
- 10d ago First seen · 65 lines · 40 tokens per session scan A 6bc633241a30
confidence-scorer is an agent published in the GitHub repository rube-de/cc-skills (10 stars, last pushed 3d ago), licensed MIT. It adds 40 tokens to every session and 908 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 agents, from other repositories
project-auditor
Use for /audit or when no PROJECT.md exists. Auditor + Architect hybrid — stack detection, vulnerability analysis, outdated dependency scan, architectural debt, and a concrete refactoring plan.
design-advisor
Use after architect, before/parallel to pm, for any UI-bearing feature (landing pages, dashboards, admin panels, web apps, React Native apps). Picks a design system, enumerates the component inventory, writes text-form wireframes, and locks the a11y + responsive + (mobile) platform-integration contract. Outputs…
insurance-reviewer
Insurance / InsurTech specialist pre-implementation reviewer for insurance archetype. Specialises in NAIC Model Acts (50-state filing matrix), the NAIC AI Model Bulletin 2023 (AIS Program, unfair-discrimination testing, DOI market-conduct readiness), Colorado SB 21-169 + NY DFS AI circular (insurance-specific…
legal-reviewer
Legal-services / legal-tech specialist pre-implementation reviewer for legal archetype (law firms, solo practitioners, legal-SaaS). Outputs threat model TM-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
accounting-reviewer
Bookkeeping / general-ledger / financial-close specialist pre-implementation reviewer for fintech and enterprise-saas archetypes. Outputs threat model TM-accounting-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
db-migration-reviewer
Database migration safety specialist. Activates when migrations/ files are detected in a PR or feature branch. Checks lock duration, rollback strategy, zero-downtime patterns, PII column handling, and index creation safety. Writes docs/migrations/MIGRATE-{slug}.md. Blocks deploy if no rollback path exists.