ooligo
claude-skill

Outside-counsel bill auditor with Claude

Difficulty
intermediate
Setup time
60min
For
legal-ops · in-house-counsel · finance-business-partner
Legal Ops

Stack

A Claude Skill that audits outside-counsel invoices line-by-line against the firm’s billing guidelines (block-billing, vague time entries, partner-staffing on associate work, double-billing of expenses, premium-time charges that violate the cap). Returns a structured audit report with per-line citations, the guideline violated, the recommended adjustment, and a confidence band — but never reduces the bill automatically. The legal-ops lead reviews and decides which adjustments to negotiate. Replaces the manual line-by-line read of a 20-page invoice with a 15-minute review of a structured report.

When to use

  • The firm has written outside-counsel billing guidelines (block-billing prohibition, time-entry minimum detail, partner/associate staffing ratios, expense reimbursement rules). Without guidelines the skill has nothing to audit against.
  • Monthly invoices from one or more named outside firms, in LEDES 1998B / 1998BI / 2000 format, or as PDF / Excel that can be parsed line-by-line.
  • The legal-ops lead or senior in-house counsel reviews the audit report before any adjustment is communicated to the outside firm. The skill writes; humans decide.

When NOT to use

  • Auto-reducing the bill without review. The skill flags; it does not adjust. Auto-deducting based on the skill’s findings damages the outside-counsel relationship, may violate the engagement letter’s dispute procedure, and exposes the firm to a fee-arbitration counterclaim. The skill’s output is decision support.
  • Disputing every flagged line. The skill catches volume that a human reviewer might miss. Picking battles is the legal-ops lead’s job; not every block-billing instance is worth the relationship cost of disputing.
  • Bills with a complex flat-fee or alternative-fee structure. The skill is calibrated to hourly billing. AFA-billed engagements need a different audit shape (deliverable completion, scope creep) that this skill does not cover.
  • Replacing e-billing platform validators. Onit, SimpleLegal, Brightflag, etc. have rule-engine validators built in. The skill is a layer ON TOP of those — for the structured-prose findings the rule engine can’t catch (“vague time entry: ‘0.6h research’” — too vague, but technically follows the format).

Setup

  1. Drop the bundle. Place apps/web/public/artifacts/outside-counsel-bill-audit-skill/SKILL.md into your Claude Code skills directory.
  2. Author the firm’s billing guidelines. Copy references/1-billing-guidelines-template.md, replace every placeholder. The guidelines should include: time-entry detail requirements, block-billing prohibition, staffing ratios (partner / senior associate / junior associate / paralegal), expense reimbursement rules, premium-time caps, scope-of-work boundaries.
  3. Configure the LEDES parser (or PDF parser for non-LEDES invoices). The bundle includes a parser that handles LEDES 1998B and 1998BI; for PDF invoices, the skill expects a pre-parsed line-item CSV.
  4. Set the per-firm calibration. Different outside firms have different baseline behavior. The skill’s output includes a per-firm calibration note (“this firm’s block-billing rate has dropped from 18% to 9% over six months”) that helps the legal-ops lead read findings in context.
  5. Dry-run on a closed month. Audit last month’s invoices. Compare the skill’s findings to the legal-ops lead’s manual review of the same invoices. Tune the guidelines if the skill flags things the lead doesn’t care about, or misses things the lead does.

What the skill does

Six steps. Deterministic checks come before the LLM evaluation, because deterministic violations (block-billing format, expense double-entry) are reproducible and don’t need model judgment.

  1. Validate the invoice format — confirm the LEDES file parses, or the CSV has the expected columns. Halt on parse failure.
  2. Run deterministic checks — block-billing detection (single time entry covering >1 task description), expense double-entry (same expense ID on two lines), staffing-ratio breach (partner hours on a task type the guidelines name as associate work), premium-time cap breach (off-hours surcharge above the contractual cap).
  3. Read the firm’s billing guidelines and the engagement letter’s specific terms. The guidelines are the comparison anchor; engagement-letter overrides are noted per matter.
  4. Per-line LLM evaluation for the cases deterministic checks can’t cover: vague time-entry descriptions, scope-creep signals, work that should have been included in a flat fee but appears as a separate line. For each finding, cite the guideline section and the specific line.
  5. Aggregate by guideline category — total hours / dollars by violation type. The aggregate is the negotiation lever, not individual lines.
  6. Emit report + audit log — structured Markdown report for the legal-ops lead, plus a JSONL audit log entry per audit run for the firm’s spend-tracking system.

Cost reality

Per invoice (typical 200-800 line items), on Claude Sonnet 4.6:

  • LLM tokens — typically 30-80k input (invoice + guidelines + skill instructions) and 5-10k output. Roughly $0.30-0.80 per invoice. Heavy invoices (>1,000 lines) may need chunking.
  • Legal-ops lead time — the win. Manual line-by-line audit of a complex invoice is 2-4 hours. Reviewing the skill’s report and deciding which findings to dispute is 20-40 minutes.
  • Setup time — 60 minutes once for the guidelines authoring; per-firm calibration is 15 minutes per firm.

Success metric

  • Adjustment rate per audit — share of audited invoices that result in a negotiated reduction. Should sit at 5-15% (above 25% means too aggressive on findings; below 2% means the skill is missing real overcharges or the guidelines are too soft).
  • Average reduction per audit — dollar value of negotiated reductions. Should be 1-4% of total invoice value at most outside firms.
  • Legal-ops lead time per invoice — should drop from 2-4 hours to 30-60 minutes (review + negotiation prep).

vs alternatives

  • vs e-billing platform rule engines. Onit / SimpleLegal / Brightflag handle the deterministic part well and are the right tool for high-volume firms. The skill is a layer ON TOP for the prose-judgment findings. Use both.
  • vs manual review. Manual is right for the smallest legal departments where invoice volume is low. The skill earns its setup cost at >5 invoices per month.
  • vs ChatGPT-style “audit this invoice.” Generic chat returns generic findings. The skill is structured: cited guideline section per finding, deterministic checks first, no auto-adjustment.

Watch-outs

  • Auto-adjustment drift. Guard: the skill’s output ends with the structured report. There is no “adjusted bill” output. The legal-ops lead is the sole adjustment authority.
  • Confidentiality of invoice content. Guard: outside-counsel invoices typically contain attorney work-product descriptions that are privileged. The skill processes locally where the calling Claude session runs — for SaaS Claude, the privilege posture is the firm’s responsibility (most BigLaw and corporate-legal departments use API access with zero-retention configuration).
  • Firm-relationship cost of over-disputing. Guard: the skill’s per-firm calibration note tracks dispute volume over time. If disputes climb, the report flags it for the legal-ops lead.
  • Guideline drift. Guard: the audit log captures the guidelines-file SHA per run. Guideline changes are visible across invoices.
  • Hallucinated guideline citations. Guard: every finding cites a specific guideline section by ID; findings without a citable section are flagged as “no matching guideline” rather than asserted.

Stack

The bundle lives at apps/web/public/artifacts/outside-counsel-bill-audit-skill/:

  • SKILL.md — the skill definition
  • references/1-billing-guidelines-template.md — fillable per-firm template
  • references/2-ledes-parser-notes.md — LEDES format parsing notes

Tools: Claude (the model). Optional: an e-billing platform (Onit, SimpleLegal) for the rule-engine layer.

Related: legal spend management, outside counsel management, alternative fee arrangements, billable hour vs AFA.

Files in this artifact

Download all (.zip)