← Finance · Asset Managers & Hedge Funds · Fund Operations & Accounting

break-trace

Vendor officialLow riskBy anthropicsLicense: Apache-2.0★ 41,232

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.

Use in Claude.ai (no code)

Download break-trace.zip
  1. In Claude.ai, open Settings → Capabilities → Skills
  2. Choose “Upload skill” and pick the zip you downloaded
  3. Turn it on, then describe your task in a chat. Claude uses the skill when it fits

Use in Claude Code and other agents

Claude Code plugin

/plugin marketplace add anthropics/financial-services
/plugin install gl-reconciler@claude-for-financial-services

skills CLI (installs every skill in the repository)

npx skills add anthropics/financial-services

Manual: Copy the plugins/agent-plugins/gl-reconciler/skills/break-trace folder to ~/.claude/skills/break-trace/

Safety scan report

Executable scripts: noneSuspicious patterns: 0Files: 1Content hash: a7064b5cea13

The scan is static pattern matching. It catches common problems and is not a guarantee of safety. Read the source before installing a skill that ships scripts.

Source

Files (1)
  • SKILL.md
SKILL.md
# 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:

```json
{
  "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.