agentmods.dev

call-agent-certainty-calibrator

call-agent-certainty-calibrator is a skill for Claude Code, Codex from CALLE-AI/awesome-phone-call-agents. It costs 82 tokens per session (1,088 once invoked), scanned A, original, MIT.

An offline checker for statements made during fact-based agent phone calls. It compares stated values with the facts supplied in the goal and call record, flagging unsupported certainty or unnecessary hedging.

In plain words
What is it for?
Use it after a fact-bearing call or before placing one to improve how known facts and missing information are worded. It cannot prove that a flagged value was invented.
Why use it?
It helps catch values the agent stated without a recorded basis and facts it presented too uncertainly.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 109repo +2 yesterday A scan 82 tokens original MIT

Good fit Use it after a fact-bearing call or before placing one to improve how known facts and missing information are worded. It cannot prove that a flagged value was invented.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/calle-ai/awesome-phone-call-agents/call-agent-certainty-calibrator
View source ↗ CALLE-AI/awesome-phone-call-agents
Install

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.

Any agent
npx skills add CALLE-AI/awesome-phone-call-agents --skill call-agent-certainty-calibrator
Clone the repo
git clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agents

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for call-agent-certainty-calibrator

README.md
[![agentmods](https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/call-agent-certainty-calibrator/github.svg)](https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/call-agent-certainty-calibrator)
Your own site
<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/call-agent-certainty-calibrator"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/call-agent-certainty-calibrator/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.

agentmods 80×15 button for call-agent-certainty-calibrator

Your own site · 80×15
<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/call-agent-certainty-calibrator"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/call-agent-certainty-calibrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,088 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00082 $0.01088
Opus 5.5 $0.00033 $0.00435
Sonnet 5.5 $0.00016 $0.00218
Haiku 4.5 $0.00008 $0.00109

Measured 26d ago against content hash d32f08e7827c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

call-agent-certainty-calibrator 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 26d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/agent_certainty_calibrator.py, scripts/test_agent_certainty_calibrator.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/call-agent-certainty-calibrator/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

call-agent-certainty-calibrator

An agent that invents specifics is worse than one that says 'I don't know'. An agent that hedges its own record is worse than useless.

Language models can express calibrated confidence in words - and, left unchecked, they drift both ways: asserting specifics nobody gave them ("free delivery on Friday!") and softening facts they were told to state ("I think it might be $45?"). On a phone call both failures are audible, and both end up in the outcome. This skill grades the agent's stated values against the goal it was given.

When To Use

  • after any fact-bearing CALL-E call, together with the goal text (or plan JSON) the call was built from
  • when an outcome contains a value nobody remembers putting in the goal
  • before placing calls, to craft wording that speaks record facts with authority and admits gaps honestly

When Not To Use

  • without the goal file; calibration is graded against the goal's facts and the CLI requires it
  • to prove the agent fabricated a value; an OVER-ASSERTED value may be true and simply missing from the goal text - the card routes to verification, always
  • on the callee's certainty; provenance-grade grades how the callee knew what they said
  • during a call; strictly post-call analysis plus pre-call goal crafting

Workflow

Audit a finished call

python3 scripts/agent_certainty_calibrator.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 fixture 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
  • over_assertions[]: agent-stated values in neither the goal facts nor any callee turn - unsourced specifics
  • over_hedges[]: goal facts spoken in a sentence with hedge words ("i think", "might be", "around", ...) and no source marker
  • calibrated_statements: goal facts stated plainly or attributed ("our records show...") - source attribution overrides a hedge
  • verdict: CALIBRATED / OVERASSERTIVE / OVERHEDGED / MIXED, plus unclear paths (empty transcript, no agent turns, goal without extractable facts)

Read the full file on GitHub · 98 lines

Files

What ships with it

8 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.

Changes

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.

  1. 26d ago First seen · 98 lines · 82 tokens per session scan A d32f08e7827c

Subscribe to this mod's changes

call-agent-certainty-calibrator is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (109 stars, last pushed yesterday), licensed MIT. It adds 82 tokens to every session and 1,088 once invoked, about $0.0003 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 2026-09-24.

Analytics and metricsBuilding agents
Related

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 83 tokens

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…

vercel/next.js · 123 tokens