What is callparity-claimkill?

A call-planning workflow for testing a quoted freight claim by asking one carefully chosen question to another party.

Use it to preview a question that could disprove an untested claim, merge quoted statements into a claim graph, and reconcile one freight fact.

It helps resolve conflicting location or product information while avoiding disclosure of the first party’s answer and avoiding unnecessary calls.

callparity-claimkill — Skill for Claude Code and Codex by CALLE-AI

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 callparity-claimkill

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/callparity-claimkill/github.svg)](https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/callparity-claimkill)

Your own site

<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/callparity-claimkill"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/callparity-claimkill/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/callparity-claimkill"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/callparity-claimkill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 929 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00044	$0.00929
Opus 5.5	$0.00018	$0.00372
Sonnet 5.5	$0.00009	$0.00186
Haiku 4.5	$0.00004	$0.00093

Measured 2mo ago against content hash 10d6ea2a6bf8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

callparity-claimkill 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 2mo ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/claimkill.py, tests/test_claimkill.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/callparity-claimkill/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ClaimKill

CallParity spends the next CALL-E call to FALSIFY a claim. The planner writes call N+1 as the cheapest question that would flip an untested or supported node to contradicted. Questions that disclose party A's answer are dropped. We do not book appointments, cascade-until-yes, or one-shot-verify a person. We reconcile one freight fact.

preview() compiles that plan from committed fixtures and places zero calls. Live CALL-E outbound is not required to run the tests. CONFIRMED is an alias of SUPPORTED.

When to use

Use this skill when two systems already disagree about one location or SKU, Party A has a quoted claim, and you need the cheapest Party B question that could flip that claim to contradicted without leaking Party A's answer.

When not to use

Do not use this skill to book appointments, run cascade-until-yes outreach, survey a person, verify identity, or place a live call without explicit approval and stored consent.

Workflow

Load a claim graph. Each node has id, text, evidence.span.quote, observable_of, and status in SUPPORTED, UNTESTED, CONTRADICTED, UNREACHABLE, ABSTAIN.
Score every RefutationQuestion with leak_score. Discard a question that discloses Party A's answer.
Keep observable questions Party B could have seen. On FR-1842, a driver question about whether dock 3 was empty stays. Any question that contains warehouse said dock 3 is dropped.
Write call N+1 as the cheapest kept question that could flip an UNTESTED or SUPPORTED node to CONTRADICTED, within the spoken-time budget.
Run scripts/claimkill.py preview --fixture fixtures/FR-1842.json. Report the plan and stop. No call is placed.
After a host returns transcript quotes, run the merger. No falsifier leaves a node UNTESTED. Voicemail or a missing transcript becomes UNREACHABLE. Confidence below 0.45 becomes ABSTAIN.

Read references/planner.md for the leak-drop algorithm. Read references/schemas.md for node, edge, and status fields.

Read the full file on GitHub · 68 lines

Files

What ships with it

9 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.

2mo ago First seen · 68 lines · 44 tokens per session scan A 10d6ea2a6bf8

Subscribe to this mod's changes

callparity-claimkill is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (112 stars, last pushed 4d ago), licensed MIT. It adds 44 tokens to every session and 929 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 2026-08-30.

Legal and compliance

callparity-claimkill next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
callparity-claimkillCALLE-AI/awesome-phone-call-agents	Skill	112	4d ago	MIT	A	44	Claude Code, Codex
fto-triageanthropics/claude-for-legal	Skill	9.9k	yesterday	Apache-2.0	A	81	Claude Code
legal-holdanthropics/claude-for-legal	Skill	9.9k	yesterday	Apache-2.0	A	68	Claude Code
specification-writingwanshuiyin/Auto-claude-code-research-in-sleep	Skill	19k	today	MIT	A	49	Claude Code
regulatory-research-fallbackHKUDS/OpenSpace	Skill	7.9k	2d ago	MIT	A	20	Claude Code, Codex
terms-of-servicegenspark-ai/genoffice	Skill	12k	yesterday	Apache-2.0	A	32	Claude Code, Codex
x-scorecardx-cmd/x-cmd	Skill	4.7k	9d ago	Apache-2.0	A	57	Claude Code, Codex