break-trace
The facts
Its description
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 the agent reads to decide when to use it.
When it starts
It starts when there is already a classified reconciliation break in hand and the agent needs to trace that break row back to the originating GL posting and subledger transaction and say what differs and why. In practice it fires once a GL-to-subledger recon has bucketed a break, or when a person asks to root-cause a specific break row.
Things a person might say (the model's guesses)
- “Here's the break row from the recon — trace it back to source and tell me why GL and the subledger disagree.”
- “Root-cause this FX break: GL shows 1,240,000 and the subledger shows something different on the same trade.”
- “Why did this GL line post on settle date while the subledger posted on trade date? Give me the root cause and owner.”
A model's summary of when it is used.
What it leads to
Other skills this one hands off to, calls, requires or offers instead, as a model read them.
What leads to it
- gl-recon hands off to this only for material breaks gl-recon, line 53
- gl-reconciler calls this gl-reconciler, line 33
Other skills that hand off to this one, call it, require it or offer it instead, as a model read them.
Licence
Apache-2.0, from LICENSE
The terms its author shares it under, which let it be shown here.
The text
Most marks come from matching words in the file, so treat them as pointers.
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.
Raw lines 1 to 9Trace path
- 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.
- Pull the subledger side — via the subledger MCP, fetch the matching transaction: trade id, trade/settle dates, counterparty, source feed, FX rate used.
- 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.
Raw lines 25 to 39From anthropics/financial-services at 6056506, 2026-10-28. Skills read by DeepSeek V4.1 Flash on 2026-11-04. Summary and techniques by Claude Opus 5.5 on 2026-11-06.