full-engagement-pipeline

full-engagement-pipeline is a skill for Claude Code from cynco-labs/ai-accounting-skills. It costs 56 tokens per session (1,753 once invoked), scanned A, original, MIT.

An end-to-end accounting workflow for turning a folder of financial documents into organised books and financial statements. It starts with intake, records progress, and handles only the required depth of work.

In plain words
What is it for?
Use it for bookkeeping jobs such as extracting data, classifying transactions, posting entries, reconciling accounts, preparing a trial balance, and producing year-end financial statement packs.
Why use it?
It gives a single starting point when someone says to do the accounting without naming a specific task. It helps organise scattered documents and stop clearly when information is missing.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/depth_gates.py <client> --strict.

Part of the accounting-engagement plugin — 45 skills shipped together

Good fit Use it for bookkeeping jobs such as extracting data, classifying transactions, posting entries, reconciling accounts, preparing a trial balance, and producing year-end financial statement packs.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/cynco-labs/ai-accounting-skills
agentmods
npx agentmods add skills/cynco-labs/ai-accounting-skills/full-engagement-pipeline

Made for: Claude Code.

Or install accounting-engagement, the plugin that ships this one along with the rest of its 45 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for full-engagement-pipeline

README.md
[![agentmods](https://agentmods.dev/badge/skills/cynco-labs/ai-accounting-skills/full-engagement-pipeline/github.svg)](https://agentmods.dev/skills/cynco-labs/ai-accounting-skills/full-engagement-pipeline)
Your own site
<a href="https://agentmods.dev/skills/cynco-labs/ai-accounting-skills/full-engagement-pipeline"><img src="https://agentmods.dev/badge/skills/cynco-labs/ai-accounting-skills/full-engagement-pipeline/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for full-engagement-pipeline

Your own site · 80×15
<a href="https://agentmods.dev/skills/cynco-labs/ai-accounting-skills/full-engagement-pipeline"><img src="https://agentmods.dev/badge/skills/cynco-labs/ai-accounting-skills/full-engagement-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,753 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00056 $0.01753
Opus 5 $0.00028 $0.00877
Sonnet 5 $0.00011 $0.00351
Haiku 4.5 $0.00006 $0.00175

Measured 12d ago against content hash dcdc61a8e4e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

full-engagement-pipeline scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

accounting-engagement/skills/full-engagement-pipeline/SKILL.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Full engagement pipeline (agent-native entry)

Purpose

Default when the human does not name a stage.
User short name: /do-books. Natural language: “do the accounting.”

You are an engagement manager — not a slash menu.

  1. Find docs (cwd, @ paths, multi-folder)
  2. One intake — shelf + register + state + ≤3 asks
  3. Run books (extract → classify → post → recon → TB)
  4. Go deeper only if engagement_type needs it
  5. Stop cleanly on blockers; depth-scoped Done when

Load first (keep light)

  1. shared/runtime-brief.md — mandatory one-screen rules (read fully)
  2. Firm profile if present (quiet defaults — no firm interview on a personal dump)
  3. Active stage skill body only (one at a time)

Open deeper docs on demand (table in runtime-brief). Do not preload kernel + shelf + operator + guardrails + … before the first file list.

Intent router

Signal Route
Resume + engagement_state.json Continue at progress; skip re-intake
Folder dump / “do accounting” This pipeline (intake → books)
Only bank recon / classify / tax / revenue / capex That narrow skill
“Set up the firm” only cold-start-interviewnot on client dumps

Folder-dump rule: no blank questionnaire. Shelf → soft-confirm → extract same session.

One intake (replaces separate shelf / setup / source ceremonies)

Do once at job start (or when new unsorted files arrive):

Step Action Artifact
Discover cwd + user paths only working list
Job map multi-entity → pick active show table if >1
Shelf clients/<slug>/source/** copy or pointer
Register coverage matrix source/register.md
State operator + engagement_type + stage engagement_state.json
Soft-confirm entity + period-on-disk structured tool ≤1
Extract start from shelf transactions.json underway

Detail if needed: shared/shelf-first.md · shared/smart-intake.md · client-workspace.
Do not run client-workspace → smart-intake → engagement-setup → source-documents as four user-facing rounds.

Read the full file on GitHub · 188 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 188 lines · 56 tokens per session scan A dcdc61a8e4e7

Subscribe to this mod's changes

full-engagement-pipeline is a skill published in the GitHub repository cynco-labs/ai-accounting-skills (3 stars, last pushed 2mo ago), licensed MIT. It adds 56 tokens to every session and 1,753 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

countbean-accounting

Rules for writing correct double-entry Beancount transactions when managing a Countbean cloud book — account naming, how to balance postings, categorisation, and safe ingestion. Use whenever recording, importing, or correcting financial data in a Countbean book.

CPUtester5465/countbean-plugin · 54 tokens

bookkeeping

Use when a small business needs audit-ready books — a chart of accounts, posting a transaction to the right account and side, clearing an uncategorized bank feed, cash vs accrual, or a ledger that won't tie to the bank. NOT interpreting the numbers — runway, burn, P&L cadence (that is finance-ops), NOT issuing…

ericrisco/rsc-harness · 84 tokens

jangbu-jongso

A Korean tax-document checklist generator for individuals, freelancers, sole-company owners, mixed earners, and certain business owners.

kimlawtech/korean-jangbu-for · 139 tokens

korean-jangbu-for

A Korean bookkeeping assistant for startups, freelancers, sole proprietors, and one-person companies. It processes financial files locally, helps classify transactions, and prepares accounting and tax outputs.

kimlawtech/korean-jangbu-for · 144 tokens

jangbu-import

A data-import workflow for turning bank files, card records, spreadsheets, receipts, tax invoices, and statement PDFs into a standard set of 13 transaction fields. OCR, or optical character recognition, is used to read information from document images and PDFs.

kimlawtech/korean-jangbu-for · 97 tokens

jangbu-connect

A setup guide for connecting Korean tax, bank, card, and social-insurance data through CODEF, an external API service. It explains how users obtain their own CODEF credentials and store them locally.

kimlawtech/korean-jangbu-for · 98 tokens