Skip to content
Agentmart
Submit a tool

reconify-engine-config

Configure Reconify from real input files.

Skill by reconifyhq

IndexedMIT★ 8
Write a review

Chalk Labs

Need help deploying reconify-engine-config?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/reconifyhq-reconify-engine-config

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Configure Reconify from real input files. Use when creating or correcting reconify.yaml, mapping columns, setting tolerances, or selecting matching passes.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/reconify-engine-config

What's inside

Skill name
reconify-engine-config
Description
Configure Reconify from real input files. Use when creating or correcting reconify.yaml, mapping columns, setting tolerances, or selecting matching passes.
License
MIT
Instructions
81 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Reconify Engine Config

Treat the installed binary and the input profiles as the sources of truth.

## 1. Load the contract

```bash
reconify capabilities
reconify config schema
```

This checkpoint is complete when the build exposes every parser, key, enum, and matching pass the
planned config requires.

## 2. Profile every source

```bash
reconify inspect INPUT
```

For each source, record candidate mappings, ambiguity flags, representative values, and the exact
date layout. This checkpoint is complete when every configured column points to an observed header
and every date layout comes from the profile or a verified sample.

## 3. Establish mapping and policy

When a config already exists, repair it instead of rewriting it. Preserve the original as
`reconify.yaml.bak`, profile every source first, and change only the mappings the profiles
contradict or `validate` and `check-source` reject. Report what you preserved and why, alongside
what you changed.

Apply these rules together with the schema:

- Resolve `file_pattern` relative to the config file.
- Use Go date layouts such as `2006-01-02`.
- Set `multiplier` from the input unit. Engine amounts and `amount_tolerance_minor` are integers in
  the resulting minor unit.
- Map `ref_col` to the shared transaction identifier. Use `group_col` when a separate grouping key
  carries one-to-many or many-to-many semantics.
- Map `name_col` when name-token matching or names in result rows are required.
- Choose one `right` or an ordered `rights` list according to the business flow.
- Select matching `passes` from `capabilities`; keep their order intentional.

When sources expose fees, taxes, commissions, or gross/net amounts, configure the optional
`parser.financials` block after ordinary mappings are proven. Map `gross_col` and `net_col`
together when settlement arithmetic is required. Add named `fields` for parsed financial values and
`expectations` for derived values. Expectation values are minor units; percentage rates are written
as percentages (`1.5` means 1.5%), and percentage bases may reference `gross`, `net`, or another
mapped financial field. Use `components` plus `operation: add` or `subtract` for a settlement
identity. Missing mapped values produce informational `financial_unchecked` findings; invalid
arithmetic or overflow is a configuration/run error.

Set tolerances from business policy. For example, a permitted difference of 2.00 with
`multiplier: 100` becomes `amount_tolerance_minor: 200`. This checkpoint is complete when every
mapping and tolerance has evidence or a named assumption.

## 4. Use inference as evidence when useful

```bash
reconify config infer LEFT RIGHT
```

The positional form is equivalent to `--left INPUT_LEFT --right INPUT_RIGHT`; do not mix the two.
Read the proposal status, reasons, alternatives, and validation counts. Confirm every proposed
mapping against the profiles before copying it. A `needs_input` proposal routes the uncertain
mappings back to inspection and user policy; it is not a terminal state.

## 5. Validate and prove every source

```bash
reconify config validate --config reconify.yaml
reconify config check-source --config reconify.yaml --source SOURCE --file INPUT
```

Run `check-source` once per configured source and rerun both checks after every correction. A config
with exactly one pair lets later `reconcile` and `verify` runs omit `--pair`. When validation fails,
fix each entry in `details.errors[]` (its `path` names the field) and rerun. Config
work is complete only when validation and all real-file source checks pass. Report the validated
config path and every assumption that affects matching.

From reconifyhq/reconify, MIT.

Signals

Stars
8
Forks
3
Open issues
13
Last commit (this folder)
Oct 7, 2026 (23 days ago)
Last release
Aug 29, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from reconifyhq

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get reconify-engine-config running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying reconify-engine-config?

CallGet help
Cite this page

reconify-engine-config skill. Agent Mart. https://agentmart.dev/skills/reconifyhq-reconify-engine-config (last updated 2026-10-24)