New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Call Sycophancy Guard

by CALLE-AI in CALLE-AI/awesome-phone-call-agents

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…

MITAuto-check passed

Install Call Sycophancy Guard

skills CLI
$ npx skills add CALLE-AI/awesome-phone-call-agents --skill call-sycophancy-guard -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install CALLE-AI/awesome-phone-call-agents call-sycophancy-guard --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agents.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/call-sycophancy-guard .claude/skills/call-sycophancy-guard && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
call-sycophancy-guard
GitHub stars
107
Token cost
~1.4k tokens
SKILL.md length
662 words
Files
9 (incl. scripts, references)
Skills in repo
101
Repo updated
First seen
Licence
MIT

At a glance

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…

  • SKILL.md covers When To Use, When Not To Use, Workflow and Scientific Foundation, plus 1 more section
  • Runs Python scripts from its folder; calls python3

What it does

Call Sycophancy Guard is an agent skill from CALLE-AI/awesome-phone-call-agents. 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.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including scripts and reference files (for example `references/example-transcript-clean.json`, `references/example-transcript-uncertain.json` and `references/example-transcript.json`).

The repository describes itself as: Portable phone-call Agent Skills, apps, examples, adapters, and scheduler recipes for AI agents. The licence is MIT.

Example prompts

  • “/call-sycophancy-guard”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 38d4118. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 2 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Call Sycophancy Guard loads about 1.4k tokens when it runs, and up to ~4.3k if it reads all its reference files. Until then it costs about 104 tokens; SKILL.md has 662 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~104
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from CALLE-AI/awesome-phone-call-agents at commit 38d4118, republished under its MIT licence (© CALLE-AI). 662 words, ~1,385 tokens.

Download SKILL.mdSave it as .claude/skills/call-sycophancy-guard/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.
name
call-sycophancy-guard
description
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.
license
MIT

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

Audit a finished call
bash
python3 scripts/sycophancy_guard.py analyze --transcript path/to/call-result.json \
  [--goal-file path/to/goal.txt]

Reads the real get_call_run result shape ({status, result: {transcript}}) or the flat shape used by sibling skill fixtures. The goal file is plain text or a JSON with a goal field. Emits a card:

  • goal_facts: amounts, dates, times extracted from the goal text
  • pushback_events[]: turn index, masked span, the responding agent turn, and its stance:
    • HOLDS - restates the record ("our records show $45")
    • CAPITULATES - adopts the contradicting value ("you're right, it is $50") without verifiable evidence
    • VERIFIES - defers to an independent channel (statement number, callback colleague, transfer)
    • UNADDRESSED - pivots away
  • outcome_taint: true when a capitulated value (a digit absent from the goal facts) reappears in a closing confirmation turn
  • verdict: CLEAN / PRESSURE_TAINTED / UNCERTAIN (UNCERTAIN when pushback was left unaddressed; stance classification runs without a goal file too, but goal facts are then empty and the taint check keys on the transcript's digits alone)
  • fields_to_verify_via_second_channel and the matching recommended action
Craft the anti-capitulation goal
bash
python3 scripts/sycophancy_guard.py craft --scenario fact-bearing-call

Emits the plan_call inputs JSON whose goal instructs the agent to hold stated facts, offer independent verification, adopt a caller's value only on verifiable information, and record both values when disagreement survives to the end.

Show full SKILL.md (246 more words)Show less

Scientific Foundation

ResearchRelevance
Towards Understanding Sycophancy in Language Models (Sharma et al., ICLR 2024, arXiv 2310.13548)Establishes sycophancy as a stable property of feedback-trained assistants and its human-feedback cause - the failure mode this skill audits
Sycophantic AI decreases prosocial intentions and promotes dependence (Cheng et al., Science 391(6792):eaec8352, 2026, doi:10.1126/science.aec8352)Measures the downstream harm: models affirm users' actions roughly 49-50% more often than humans, and sycophantic affirmations change what users then do
SycEval: Evaluating LLM Sycophancy (Fanous et al., AIES 2025, arXiv 2502.08177)Multi-turn sycophancy measurement; its progressive-opinion-shift framing informs this skill's pushback-then-stance sequence over a call

Citation notes recorded during verification: the Cheng et al. paper is in Science Vol 391 Issue 6792 (journal version 2026; preprint arXiv 2510.01395, October 2025), and SycEval appeared at AIES 2025 (AAAI/ACM Conference on AI, Ethics, and Society), not the AAAI main track. This skill detects overt stance switches in text only; it has no access to the agent's internals and labels every output analysis_mode: "heuristic".

Differences from sibling skills

  • call-emotional-contagion-monitor tracks affect transferring between speakers; this skill tracks epistemic stance - what the agent claims is true - under social pressure.
  • call-negotiation-coach coaches strategy (BATNA, concessions) where flexibility is legitimate; this skill guards facts where folding without evidence corrupts the record.
  • call-rlhf-self-reflection-scorer judges overall call quality; this skill isolates one specific, well-documented failure mode and ties it to outcome integrity.
  • call-review checks claim support in the transcript; it does not ask whether the agent switched positions mid-call under pressure.

© CALLE-AI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 8 other files (scripts, references) in skills/call-sycophancy-guard of CALLE-AI/awesome-phone-call-agents.

  • SKILL.md
  • references/example-goal.txt
  • references/example-transcript-clean.json
  • references/example-transcript-uncertain.json
  • references/example-transcript.json
  • references/examples.md
  • references/safety.md
  • scripts/sycophancy_guard.py
  • scripts/test_sycophancy_guard.py

Open the folder on GitHubat commit 38d4118

Compare with similar skills

Call Sycophancy Guard next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Call Sycophancy Guard compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Call Sycophancy Guard this skillCALLE-AI/awesome-phone-call-agents107—~1.4kAutomated safety check: PassMIT
Safety Guardaffaan-m/ECC277k2 repos~554Automated safety check: NotesMIT
Baoyu Youtube TranscriptJimLiu/baoyu-skills27k1 repos~2.4kAutomated safety check: PassMIT
Youtube Transcriptbrowser-act/skills6.1k—~2.1kAutomated safety check: PassMIT
Youtube Transcriptsickn33/agentic-awesome-skills47k1 repos~1.3kAutomated safety check: PassMIT
Transcription0xsline/OpenChatCut2.2k1 repos~1.1kAutomated safety check: PassAGPL-3.0

Similar skills

  • Safety Guard

    affaan-m/ECC

    Guard against destructive operations with three modes: Careful intercepts dangerous commands (rm -rf, git push --force, DROP TABLE) for confirmation, Freeze locks writes to one directory, and Guard…

    277k GitHub starsUsed in 2 repos~554 tokens
    DevelopmentAuto-check: notes

  • Baoyu Youtube Transcript

    JimLiu/baoyu-skills

    Downloads YouTube video transcripts/subtitles and cover images by URL or video ID.

    27k GitHub starsUsed in 1 repo~2.4k tokens
    Media & CreativeAuto-check passed

  • Youtube Transcript

    browser-act/skills

    YouTube transcript extraction and content reformatting: given a YouTube video URL, opens the video's transcript panel, extracts all timestamped segments, and transforms the raw transcript into…

    6.1k GitHub stars~2.1k tokensUpdated 1 mo ago
    Knowledge ManagementAuto-check passed

  • Youtube Transcript

    sickn33/agentic-awesome-skills

    Fetch YouTube transcripts through DeepAPI or local fallback tooling and save clean text output.

    47k GitHub starsUsed in 1 repo~1.3k tokens
    Knowledge ManagementAuto-check passed

  • Transcription

    0xsline/OpenChatCut

    A skill your agent uses when a video/audio task needs OpenChatCut transcription, captions, subtitles, subtitle styling, transcript search, transcript readiness checks, or enabling captions…

    2.2k GitHub starsUsed in 1 repo~1.1k tokens
    Media & CreativeAuto-check passed

  • Guard Mode

    garrytan/gstack

    Switches on full safety by combining warnings before destructive commands with a block on edits outside one directory you choose, for work on production or live systems.

    136k GitHub stars~1k tokensUpdated today
    Agent WorkflowsAuto-check: notes

More from CALLE-AI/awesome-phone-call-agents

All 101 skills in this repo

  • Accessible Outing Verifier

    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.

    107 GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed

  • Ground Truth Gate

    CALLE-AI/awesome-phone-call-agents

    A skill your agent uses when an agent holds some evidence for a physical-world claim but the evidence is broader, narrower, or older than the exact question asked, and it must first decide whether a…

    107 GitHub stars~3.3k tokensUpdated yesterday
    Auto-check passed

  • Is It Accessible

    CALLE-AI/awesome-phone-call-agents

    Call a venue and ask the accessibility questions that matter to one specific person — step-free entry, hearing loop, guide dogs, quiet hours, changing places — then return a per-need verdict backed…

    107 GitHub stars~4.3k tokensUpdated yesterday
    Auto-check passed

  • Landmark Navigation Assist

    CALLE-AI/awesome-phone-call-agents

    Turns a pre-written, building-level location config into a CALL-E outbound phone-call task that guides a delivery driver through the last few hundred metres to a specific building using landmarks…

    107 GitHub stars~1.6k tokensUpdated yesterday
    Auto-check passed

  • Research Gap Call Verifier

    CALLE-AI/awesome-phone-call-agents

    Turn cited business research into a bounded, approval-gated phone-call plan that asks only unresolved factual questions, then reconcile CALL-E-compatible results without treating voicemail, refusal…

    107 GitHub stars~1.7k tokensUpdated yesterday
    Auto-check passed

  • Structured Outcome Followup Call

    CALLE-AI/awesome-phone-call-agents

    Place a goal-driven CALL-E call that collects specific structured answers, score those answers against a deterministic rubric you supply, and conditionally trigger a follow-up action — all runnable…

    107 GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed

Questions about Call Sycophancy Guard

What does Call Sycophancy Guard 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…. Call Sycophancy Guard is an agent skill from CALLE-AI/awesome-phone-call-agents. 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.

How do I install Call Sycophancy Guard in Claude Code?

Run `npx skills add CALLE-AI/awesome-phone-call-agents --skill call-sycophancy-guard -a claude-code`. Or copy the skill folder (skills/call-sycophancy-guard in CALLE-AI/awesome-phone-call-agents) into .claude/skills/call-sycophancy-guard in your project. Claude Code loads it when a task matches its description.

How do I install Call Sycophancy Guard in Codex?

Run `npx skills add CALLE-AI/awesome-phone-call-agents --skill call-sycophancy-guard -a codex`. Or copy the skill folder (skills/call-sycophancy-guard in CALLE-AI/awesome-phone-call-agents) into .agents/skills/call-sycophancy-guard in your project. Codex loads it when a task matches its description.

Can I use Call Sycophancy Guard in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add CALLE-AI/awesome-phone-call-agents --skill call-sycophancy-guard -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/call-sycophancy-guard, .gemini/skills/call-sycophancy-guard, .github/skills/call-sycophancy-guard and .opencode/skills/call-sycophancy-guard in your project.

What does Call Sycophancy Guard need to run?

Going by SKILL.md and its folder, Call Sycophancy Guard needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Call Sycophancy Guard access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Call Sycophancy Guard safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Call Sycophancy Guard use?

Call Sycophancy Guard is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Call Sycophancy Guard use?

About 1.4k tokens (SKILL.md is roughly 5.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.9k tokens, read only when the agent opens those files.

What are the alternatives to Call Sycophancy Guard?

Skills that share tags, products or a category with Call Sycophancy Guard: Safety Guard (affaan-m/ECC, 277k stars), Baoyu Youtube Transcript (JimLiu/baoyu-skills, 27k stars), Youtube Transcript (browser-act/skills, 6.1k stars) and Youtube Transcript (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Call Sycophancy Guard?

CALLE-AI (a GitHub organization) maintains it in CALLE-AI/awesome-phone-call-agents, which has 107 GitHub stars. The repository holds 101 skills in this directory. The repository was last updated on October 10, 2026.

Source: CALLE-AI/awesome-phone-call-agents on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.