AutoGineer
Generated banner for Break Trace
Generated logo for Break Trace

Break Trace

AnthropicOfficialPublished by Anthropic

  • Skill
  • Research and analysis
  • Business and productivity
  • Apache-2.0
  • No issues found
Download ZIP

From the author

Root-cause a reconciliation break to its source transaction or posting — follow the audit trail from the break row back to the originating entry on each side and state what differs and why. Use after gl-recon has classified a break.
— the description by Anthropic

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

break-trace is a diagnostic skill designed to investigate reconciliation breaks identified by gl-recon. It systematically traces a break back to its originating transactions on both the General Ledger and subledger sides, compares key attributes, and generates a structured root-cause analysis. The skill identifies the specific discrepancy, assigns ownership, and recommends an action, providing clear insights for financial operations teams without performing any ledger adjustments itself.

What it does

  • Fetches GL journal entries and postings via internal-gl MCP.
  • Retrieves matching subledger transactions via subledger MCP.
  • Compares attributes like dates, FX rates, and account mappings to identify discrepancies.
  • Generates a concise, single-sentence root-cause statement.
  • Categorizes the break by owner, expected resolution date, and recommended action.

When to use it

  • Immediately after a reconciliation break has been classified by gl-recon.
  • When you need to determine why a specific GL line does not match its subledger counterpart.
  • To identify whether a break is caused by timing, FX rates, mapping errors, or duplicate entries.
  • When preparing documentation for accounting or reference data teams to resolve a break.

Advantages

  • Provides a standardized format for root-cause reporting.
  • Reduces manual investigation time by automating the retrieval of source data.
  • Clearly identifies the responsible party for each type of break.
  • Prevents unauthorized adjustments by focusing strictly on diagnosis.

Usage examples

“Trace the break for key 99821 identified by gl-recon.”
The agent retrieves the GL and subledger entries, compares the attributes, and returns a JSON object stating the cause (e.g., a mapping error), the owner, and the recommended action.
“Why is there a discrepancy in the trade for account 11420?”
The agent performs a trace, identifies that the subledger used a different FX rate than the GL, and outputs the specific FX break details.

Install

  1. Download the skill as a ZIP:

    https://mp-staging.autogineer.com/agent-skills/anthropics/break-trace/download

  2. Unzip it into the cross-client skills folder of your project:

    mkdir -p .agents/skills && unzip break-trace.zip -d .agents/skills

Documentation by Anthropic

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.

Files

Requirements and compatibility

Written for: Claude Code, Claude apps

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Security

No issues found by our static scan· No issues found

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Published by
Anthropic
Publisher
Anthropic (Official)
Source
anthropics/financial-services · plugins/agent-plugins/gl-reconciler/skills/break-trace · commit 6056506
Licence
Apache License 2.0 (redistribution allowed)
  • LICENSE (added by AutoGineer from LICENSE)
  • ATTRIBUTION.md (written by AutoGineer)
Synced
Also distributed in
anthropics/financial-services

AutoGineer is not affiliated with or endorsed by Anthropic.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download break-trace.zip