break-trace

break-trace is a skill for Claude Code from anthropics/financial-services. It costs 50 tokens per session (479 once invoked), scanned A, original, Apache-2.0.

A root-cause investigation for one reconciliation break, meaning a difference between two accounting records. It follows each side back to the original journal entry or trade and explains which detail differs and why.

In plain words
What is it for?
Use it after a general-ledger-to-subledger reconciliation identifies a break. It compares posting dates, rates, accounts, quantities, amounts, and source transactions to produce a one-sentence explanation.
Why use it?
It removes guesswork when a balance does not match. The result provides an audit trail that shows whether the issue comes from timing, exchange rates, account mapping, duplicate data, or another source.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the gl-reconciler plugin — 2 skills, 1 agent shipped together

About the project

Claude for Financial Services is a collection of agents, skills, commands, plugins, and data connectors for investment banking, equity research, private equity, and wealth-management workflows. Financial professionals use it to draft models, memos, research notes, and reconciliations for review by qualified people. The catalogue contains components from these workflows, including agents, skills, plugins, commands, and instructions.

anthropics/financial-services · 34,705 stars · on GitHub

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.

agentmods
npx agentmods add skills/anthropics/financial-services/break-trace
Any agent
npx skills add anthropics/financial-services --skill break-trace
Clone the repo
git clone --depth 1 https://github.com/anthropics/financial-services

Made for: Claude Code.

Or install gl-reconciler, the plugin that ships this one along with the rest of its 2 skills, 1 agent.

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 break-trace

README.md
[![agentmods](https://agentmods.dev/badge/skills/anthropics/financial-services/break-trace.svg)](https://agentmods.dev/skills/anthropics/financial-services/break-trace)
Your own site
<a href="https://agentmods.dev/skills/anthropics/financial-services/break-trace"><img src="https://agentmods.dev/badge/skills/anthropics/financial-services/break-trace.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 479 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00050 $0.00479
Opus 5 $0.00025 $0.00239
Sonnet 5 $0.00010 $0.00096
Haiku 4.5 $0.00005 $0.00048

Measured 6d ago against content hash a7064b5cea13, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

break-trace 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 6d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

plugins/agent-plugins/gl-reconciler/skills/break-trace/SKILL.md · 40 lines

What it actually says

Root-cause a break

Given a single break row (key, GL values, subledger values, bucket, likely cause), trace it to source and produce a root-cause statement.

Trace path

  1. Pull the GL side — via the internal-gl MCP, fetch the journal entry or posting that produced this GL line: entry id, posting date, source system, batch id, preparer.
  2. Pull the subledger side — via the subledger MCP, fetch the matching transaction: trade id, trade/settle dates, counterparty, source feed, FX rate used.
  3. Diff the attributes — line up posting date, FX rate/date, account mapping, quantity sign, amount sign. The differing attribute is usually the cause.

Cause → statement

Write the root cause as a single sentence in the form "⟨side⟩ ⟨did what⟩ because ⟨reason⟩", e.g.:

  • "GL posted on settle date (T+2) while subledger posted on trade date — timing break, will clear on 2026-05-07."
  • "Subledger used WM/R 4pm rate; GL used Bloomberg close — FX break of 12 bps on the base amount."
  • "Security ABC123 maps to GL account 11420 in the mapping table but the subledger fed 11410 — mapping break, raise to reference-data."
  • "Subledger posted the trade twice (trade ids 88412 and 88419 are duplicates) — duplicate post, suppress 88419."

Output

For each traced break, return:

{
  "key": "...",
  "root_cause": "one sentence as above",
  "owner": "ops | reference-data | accounting | upstream-system",
  "expected_clear_date": "YYYY-MM-DD or null",
  "action": "monitor | adjust | raise-ticket | suppress"
}

Only the resolver writes adjustments — this skill diagnoses, it does not post.

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. 6d ago First seen · 40 lines · 50 tokens per session scan A a7064b5cea13

Subscribe to this mod's changes

break-trace is a skill published in the GitHub repository anthropics/financial-services (34,705 stars, last pushed 11d ago), licensed Apache-2.0. It adds 50 tokens to every session and 479 once invoked, about $0.0003 per session on Opus 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.

Related

Other skills, from other repositories

backtest-diagnose

Diagnose failed or underperforming backtests, locate the root cause, and fix the issue.

HKUDS/Vibe-Trading · 25 tokens

health

Runs a budget-aware agent-assisted engineering health audit for instruction/config drift, hooks/MCP, verifier surfaces, and AI maintainability. Use when users ask in any language to audit Claude, Codex, Pi, agent instructions, MCP or hooks, verifier coverage, or AI-maintainability drift. Not for debugging application…

tw93/Waza · 71 tokens

tick-collection-ops

Operate and troubleshoot the MT5 tick collection system. HOST MOVED 2026-08-07 - MT5 now runs on the FXView VPS (Windows scheduled tasks, C:\odb-tickrings), NOT gpu-host-1/Linux-Wine/systemd. EA, ring format and gap-detection reasoning unchanged. Covers gap detection, restart recovery, daily ops.

terrylica/cc-skills · 80 tokens

chart-indicator

Build a custom indicator for the OpenAlgo /trading charting terminal (openalgo-charts). Use when asked to create, port, or debug a chart indicator, overlay, oscillator, band, or on-chart signal, including porting a study written for another charting platform. Writes a plain-JS descriptor into strategies/indicators/…

marketcalls/openalgo · 102 tokens

desk-incident-response

What the desk does when something goes wrong on Hyperliquid - unknown send results, unexpected fills or positions, unprotected positions, stuck or orphaned orders, API outages, rate limiting, and suspected API wallet compromise. Contain first, reconcile from the exchange record, act only through approved tickets, then…

galleonlabs/hypergrok-trading-desk · 78 tokens

flow-builder

Build, edit or debug an OpenAlgo Flow workflow - the no-code node graph at /flow. Use when asked to create a workflow, wire a webhook or TradingView alert to an order, add a node, port a strategy into Flow, or work out why a workflow imported but did nothing. Produces a workflow JSON that is validated against the real…

marketcalls/openalgo · 81 tokens