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 CALLE-AI/awesome-phone-call-agents --skill call-rlhf-self-reflection-scorergit clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agentsWrote 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/calle-ai/awesome-phone-call-agents/call-rlhf-self-reflection-scorer)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/call-rlhf-self-reflection-scorer"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/call-rlhf-self-reflection-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/skills/calle-ai/awesome-phone-call-agents/call-rlhf-self-reflection-scorer"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/call-rlhf-self-reflection-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 | $0.00047 | $0.00641 |
| Opus 5.5 | $0.00019 | $0.00256 |
| Sonnet 5.5 | $0.00009 | $0.00128 |
| Haiku 4.5 | $0.00005 | $0.00064 |
Grade A, and why
call-rlhf-self-reflection-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 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RLHF Self-Reflection Scorer
This skill demonstrates post-call QA with a small lexical scorer. It accepts a supplied transcript and optional rating, then returns predefined review suggestions. It does not collect user feedback, call an LLM, train a model, store RAG memories, or apply prompt changes. These are possible future host integrations, not delivered behavior.
Scientific Foundation
| Paper / Concept | Relevance |
|---|---|
| LLM-as-a-Judge | Using a strong LLM to evaluate the outputs of an agentic LLM correlates highly with human CSAT (Customer Satisfaction). |
| Self-Reflection (Reflexion) | Agents that critique their own past transcripts and generate "verbal reinforcement" prompts perform significantly better on subsequent tasks. |
| RLHF (Reinforcement Learning from Human Feedback) | Incorporating explicit user scores (if provided post-call) alongside automated critiques bridges the gap between simulated and real-world quality. |
How it works
- The skill receives the transcript and any explicit CSAT score given by the user (if applicable).
- If the user gave a high score (>= 4), the interaction is marked as successful.
- If the score is low or missing, the skill checks a small set of text patterns and returns a mocked critique; it cannot establish a root cause.
- It outputs an
EvaluationResultcontaining the score, the identified critique, and a specific system prompt recommendation to fix the behavior.
Decision Matrix
| Explicit Score | Transcript Sentiment | Outcome | Action |
|---|---|---|---|
>= 4 |
Any | EXPLICIT_USER (High) |
Maintain current strategy |
< 4 |
Any | SELF_CRITIQUE |
Return a heuristic critique; not an explanation of the user's rating |
None |
Smooth | SELF_CRITIQUE (High) |
Baseline evaluation |
None |
Friction detected | SELF_CRITIQUE (Low) |
Flag friction point and generate patch |
Expected Outcomes & Metrics
These are unvalidated targets for a possible future evaluator, not measurements of this mock scorer.
What ships with it
5 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.
- 1mo ago First seen · 47 lines · 47 tokens per session scan A 89445b7954b4
call-rlhf-self-reflection-scorer is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (109 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 641 once invoked, about $0.0002 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 2026-09-19.
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…
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…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…