Call Sycophancy Guard

Offline experimental CALL-E transcript helper that detects pushback against goal-grounded facts and classifies the agent's response (HOLDS, CAPITULATES, VERIFIES, UNADDRESSED), flags capitulated values that tainted the final confirmation, and crafts anti-capitulation goals. It is not a measure of the agent's intent, proof the callee was wrong, or authorization to act on the call's outcome.

116 stars 512 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add CALLE-AI/awesome-phone-call-agents --skill call-sycophancy-guard
Manual install
git clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agents.git /tmp/awesome-phone-call-agents
mkdir -p ~/.claude/skills
cp -r /tmp/awesome-phone-call-agents/skills/call-sycophancy-guard ~/.claude/skills/call-sycophancy-guard

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# call-sycophancy-guard

> **An agent that agrees with everything confirms nothing.**

Language models are demonstrably sycophantic: trained on human feedback,
they affirm users far more often than humans do, and that behavior survives
into deployed assistants. On a phone call this has a specific cost: the
callee pushes back on a fact - "no, it's $50" - and the agent folds, not
because it saw evidence, but because agreeing is polite. The closing
confirmation then repeats the adopted value, and whatever parses that
outcome writes a fact nobody established. This skill catches exactly that
sequence.

## When To Use

- after any CALL-E call whose result contains amounts, dates, or times the
  callee disputed, and before the outcome is written anywhere
- with the goal text (or plan JSON) the call was built from, so ground
  facts can be extracted and checked against adopted values
- before placing a fact-bearing call, to craft a goal that holds facts
  without being rude

## When Not To Use

- to prove the callee was wrong: a capitulation is an unverified stance
  switch, and the callee holding a paper invoice may well be right; the
  card routes to verification, never to reversal
- to detect emotional pressure or hostility; use `call-fraud-shield` for
  scam patterns and `call-emotional-contagion-monitor` for affect
- during a call; this is strictly post-call analysis plus pre-call goal
  crafting, because CALL-E exposes transcripts, not live audio

## Workflow
Read the full skill on GitHub

Details

Skill name
call-sycophancy-guard
Path
skills/call-sycophancy-guard/SKILL.md
License
MIT
Repo updated
14 November 2026

FAQ

What does the Call Sycophancy Guard skill do?

Offline experimental CALL-E transcript helper that detects pushback against goal-grounded facts and classifies the agent's response (HOLDS, CAPITULATES, VERIFIES, UNADDRESSED), flags capitulated values that tainted the final confirmation, and crafts anti-capitulation goals. It is not a measure of the agent's intent, proof the callee was wrong, or authorization to act on the call's outcome.

How do I install the Call Sycophancy Guard skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add CALLE-AI/awesome-phone-call-agents --skill call-sycophancy-guard. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Call Sycophancy Guard popular?

It lives in CALLE-AI/awesome-phone-call-agents, which has 116 GitHub stars and 512 forks.

Related skills

Accesscall

116

CALLE-AI/awesome-phone-call-agents

Conduct phone-based accessibility intake interviews for users who cannot complete web-based accessibility audit forms (screen reader fatigue, motor impairment, low vision, cognitive load), and produce a structured result mapped to VPAT 2.4 / Section 508 conformance reporting fields.

Frontend & Design512

Accessible Outing Verifier

116

CALLE-AI/awesome-phone-call-agents

Demonstrates advisory accessibility-planning checks with offline fixtures and a proposed bounded CALL-E workflow; use for exploring unknown or qualified venue claims without making calls.

Frontend & Design512

Adherence Memory Callback

116

CALLE-AI/awesome-phone-call-agents

Run a consent-based outbound CALL-E medication-adherence phone check-in that remembers each caller across calls, learns side-effect patterns across many callers behind a corroboration gate, and honors "call me back later" by opening the next call with that context.

Productivity & Notes512

Dialtone Handshake

116

CALLE-AI/awesome-phone-call-agents

Use when an AI phone call agent (outbound caller or inbound voicebot) needs to recognise that the other end of the call is also an AI, switch to a compressed machine mode, and label call results by who actually attested them (human, phone system, or AI agent).

AI, LLMs & Agents512

Call Semantic Barge in Analyzer

116

CALLE-AI/awesome-phone-call-agents

Post-call cooperation skill. Classifies callee turns in a CALL-E transcript as backchannels ("mm-hmm", "right, okay"), frustration barge-ins ("wait", "hold on", "slow down"), or substantive answers - disambiguating answers from backchannels via the preceding agent question - and computes pacing metrics including backchannel density and whether the agent shortened its turns after the first interruption. Returns a cooperation profile (ENGAGED_COOPERATIVE / NEUTRAL / FRUSTRATED_INTERRUPTING / DISENGAGED) with a pacing recommendation and a ready-to-use pacing goal for the next plan_call. Heuristic

AI, LLMs & Agents512

Dollar Consent First Callback

116

CALLE-AI/awesome-phone-call-agents

Place one consent-first CALL-E callback after a local safety gate has already blocked an extreme-risk developer action, so a known project owner can say stop or request normal review without granting the agent destructive permission.

AI, LLMs & Agents512

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.