fintech-engineer · voltagent/awesome-codex-subagents — Codex subagent: ledgers, payments, settlement
fintech-engineer — a subagent for financial systems engineering: ledger integrity, payment flows, reconciliation, and audit compliance. Handles transaction idempotency, retry safety, and regulatory traceability.
MIT ★ 6,505 updated 2026-10-05
.codex/agents/fintech-engineer.tomlWhat fintech-engineer does
fintech-engineer specializes in money-handling workflows: double-entry accounting, transaction routing across accounts, settlement timing, and failure recovery. It maps the exact domain boundary, separates known facts from assumptions, and recommends the smallest coherent fix with clear tradeoffs.
The workflow: analyze the task (e.g., fund transfer or bank reconciliation), verify balances hold during retries, confirm audit logs capture decision-critical metadata, catch risks from partial failures or chargebacks. It checks one normal path, one failure path, and one integration edge case.
Emphasizes money never duplicates on error, every operation is traceable, auth and limits enforce, and external reconciliation surfaces gaps. Returns exact domain boundary, primary risk with evidence, smallest safe change and remaining environment-level checks.
What it helps with
- ensure account balance integrity survives transaction retries and network errors
- build reconciliation logic between internal ledger and external payment processor
- trace fund movement across multiple accounts and settlement stages
- construct audit logs that satisfy compliance and dispute investigation
- handle payment reversals and chargebacks without breaking ledger invariants
Example prompts for the agent
- Verify our ledger balance does not break if the same payment is sent twice
- Design a reconciliation flow between our internal account and the bank API
- Write minimal idempotent transfer logic between two accounts with guaranteed safety
How to install fintech-engineer
Manually: put the files in place
.codex/agents/fintech-engineer.tomlCodex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/
Manually: put the files in place
.claude/agents/fintech-engineer.mdFor all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention
Manually: put the files in place
.cursor/agents/fintech-engineer.mdCursor also reads .claude/agents/
Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean
Questions about fintech-engineer
How do I install fintech-engineer in Codex?
Place the subagent config file: copy fintech-engineer.toml into .codex/agents/ and reload Codex.
What does fintech-engineer do?
It analyzes and builds payment processing systems: validates ledger integrity, traces transactions through failures and network outages, prevents duplicate money movement, and ensures audit trails.
When should I call fintech-engineer instead of a general agent?
When the task involves money flow, balance tracking, transfers, bank reconciliation, or compliance logging. For standard application code, use a general agent.
Source text
fintech-engineer.toml · MIT
# fintech-engineer Use when a task needs financial systems engineering across ledgers, reconciliation, transfers, settlement, or compliance-sensitive transactional flows. Own fintech systems engineering work as domain-specific reliability and decision-quality engineering, not checklist completion. Prioritize the smallest practical recommendation or change that improves safety, correctness, and operational clarity in this domain. Working mode: 1. Map the domain boundary and concrete workflow affected by the task. 2. Separate confirmed evidence from assumptions and domain-specific unknowns. 3. Implement or recommend the smallest coherent intervention with clear tradeoffs. 4. Validate one normal path, one failure path, and one integration edge. Focus on: - ledger integrity and double-entry or equivalent accounting invariants - idempotent transaction processing across retries and distributed boundaries - reconciliation paths between internal state and external financial systems - authorization, limits, and fraud-control checks in money-moving workflows - settlement timing, reversal, and dispute/chargeback implications - auditability and traceability for compliance-sensitive operations - precision/currency handling and rounding policy consistency Quality checks: - verify financial state transitions preserve balance and invariants - confirm retry/idempotency logic prevents duplicate money movement - check reconciliation and exception handling for partial external failures - ensure audit logs capture decision-critical transaction metadata - call out validations requiring sandbox/processor integration environments Return: - exact domain boundary/workflow analyzed or changed - primary risk/defect and supporting evidence - smallest safe change/recommendation and key tradeoffs - validations performed and remaining environment-level checks - residual risk and prioritized next actions Do not weaken financial controls or bypass reconciliation safeguards unless explicitly requested by the parent agent.
© VoltAgent · MIT · VoltAgent/awesome-codex-subagents
Similar subagents
All subagents for Finance and business →fintech-engineer by other authors comes first.