adjudication-sheets

adjudication-sheets is a skill for Claude Code from kennethkhoocy/applied-micro-skills. It costs 142 tokens per session (1,112 once invoked), scanned A, original, MIT.

A process for creating sheets where people review and label cases produced by language-model pipelines. It preserves the full evidence used by the model and keeps multi-line text readable in spreadsheet programs.

In plain words
What is it for?
It is for preparing CSV or Excel adjudication sheets, tracing the exact text sent to a model, preserving complete evidence, and supporting human rulings on classifier or rater results.
Why use it?
Short excerpts can hide the sentence needed for a decision, while line breaks can make populated CSV cells look empty or broken. Matching the review sheet to the model's actual input prevents unreliable labels.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the applied-micro plugin — 17 skills shipped together

Good fit It is for preparing CSV or Excel adjudication sheets, tracing the exact text sent to a model, preserving complete evidence, and supporting human rulings on classifier or rater results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kennethkhoocy/applied-micro-skills/adjudication-sheets
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add kennethkhoocy/applied-micro-skills --skill adjudication-sheets
Clone the repo
git clone --depth 1 https://github.com/kennethkhoocy/applied-micro-skills

Made for: Claude Code.

Or install applied-micro, the plugin that ships this one along with the rest of its 17 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 adjudication-sheets

README.md
[![agentmods](https://agentmods.dev/badge/skills/kennethkhoocy/applied-micro-skills/adjudication-sheets/github.svg)](https://agentmods.dev/skills/kennethkhoocy/applied-micro-skills/adjudication-sheets)
Your own site
<a href="https://agentmods.dev/skills/kennethkhoocy/applied-micro-skills/adjudication-sheets"><img src="https://agentmods.dev/badge/skills/kennethkhoocy/applied-micro-skills/adjudication-sheets/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 adjudication-sheets

Your own site · 80×15
<a href="https://agentmods.dev/skills/kennethkhoocy/applied-micro-skills/adjudication-sheets"><img src="https://agentmods.dev/badge/skills/kennethkhoocy/applied-micro-skills/adjudication-sheets.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 142 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,112 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00142 $0.01112
Opus 5 $0.00071 $0.00556
Sonnet 5 $0.00028 $0.00222
Haiku 4.5 $0.00014 $0.00111

Measured 11d ago against content hash 1456b3dc441b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

adjudication-sheets 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 11d 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.

plugins/applied-micro/skills/adjudication-sheets/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Human Adjudication Sheets from LLM-Pipeline Data

Problem

Adjudication sheets built from pipeline intermediates tend to carry truncated "excerpt" columns (previews made for machine diffing, not human judging). A human asked to rule "does this text show X?" on a fragment produces invalid rulings: the decisive sentence may sit past the cutoff. Separately, multi-line text in CSV cells renders as broken rows/empty cells in Excel, so the labeler reports "there is no data here" even when the column is populated.

Context / Trigger Conditions

  • A labeler says the sheet has "no information" — check for embedded newlines in CSV fields first.
  • Excerpt lengths cluster at an exact value (all 1,204 / 1,500 / 800 chars) or end with "[…]" — that is a hard cap, not natural length.
  • The ruling question is "does the record/text show X?" — the ruling basis must be byte-identical to what the classifier/raters saw, or the ruling grades a different object.

Solution

  1. Trace the true rating basis from the scoring code, not from intermediates. Find the line where text is passed to the model (e.g. prompt = ... + text) and reproduce that construction exactly. Verify: stored excerpt == full_text[:cap] (0 mismatches), or cache-key match against the LLM request cache.
  2. Deliver .xlsx, not .csv, for any sheet with multi-line text: wrap_text + frozen header + generous width on evidence columns; data-validation dropdown on the ruling column with the exact allowed codes (e.g. E_pos/E_neg/unclear, or 0/1/2/unclear).
  3. Handle the Excel cell cap (32,767 chars) explicitly: if full text exceeds it, inline the first ~30k ending with a loud marker ("[CONTINUES — see companion file]") AND write the complete text to a per-case .txt (header block with case metadata + full text); add a text_file path column. Write companion files for ALL cases regardless — they are the comfortable reading surface.
  4. Keep the original CSV untouched as the machine-readable artifact; the xlsx is the human ruling surface; harvest rulings from the xlsx. Distribution: text_file paths are project-relative and break the moment the sheet is emailed or copied out of the tree (the labeler asks "where are the attendant/companion files?"). If the labeler is not working inside the project folder, ship ONE zip containing the xlsx and the companion-texts folder side by side, with the instruction: extract together; the file for row X is <texts_folder>\<case_id>.txt next to the spreadsheet. Require the FILLED xlsx back and harvest from the returned copy, not the original.
  5. Tell the labeler the epistemics: rule from the provided record only; silence = negative; outside research (Google) goes in ruling_notes, never the ruling — otherwise the labels leak information the classifier could never see.

Read the full file on GitHub · 51 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 51 lines · 142 tokens per session scan A 1456b3dc441b

Subscribe to this mod's changes

adjudication-sheets is a skill published in the GitHub repository kennethkhoocy/applied-micro-skills (28 stars, last pushed 6d ago), licensed MIT. It adds 142 tokens to every session and 1,112 once invoked, about $0.0007 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 2026-08-30.

Related

Other skills, from other repositories

stylework-yunxiao-requirement-sync

A workflow for exporting selected requirements from Yunxiao, a project-management service, into a new sheet in an existing DingTalk online spreadsheet. It formats the result into a fixed set of columns and groups it by iteration.

PANGKAIFENG/ai-product-manager-skills · 153 tokens

submittal-log-generator

Extract all submittal requirements from specification sections and generate a comprehensive submittal register in Excel. Triggers: 'submittal log', 'extract submittals', 'submittal register'. Requires /spec-splitter output.

dleerdefi/claude-code-construction · 55 tokens

schedule-extractor

Extract tabular schedule data from construction drawings — door, window, finish, fixture, panel schedules — and output to Excel. Triggers: 'door schedule', 'extract schedule', 'schedule to Excel', 'panel schedule'.

dleerdefi/claude-code-construction · 49 tokens

tag-audit-and-takeoff

Count-based quantity takeoff and tag completeness auditing for construction drawings. Vision + OCR reconciliation, sheet markup, Excel QTO output. Triggers: 'tag audit', 'quantity takeoff', 'QTO', 'count fixtures'.

dleerdefi/claude-code-construction · 54 tokens

bid-tabulator

Extract data from subcontractor bid PDFs and produce a comparison spreadsheet. Feeds into /bid-evaluator. Triggers: 'tabulate bids', 'bid comparison', 'compare bids', 'buyout analysis', 'bid tab'.

dleerdefi/claude-code-construction · 50 tokens

docs-pipeline-automation

Build repeatable data-to-Docs pipelines from Sheets and Drive sources. Use for automated status reports, template-based document assembly, and scheduled publishing workflows.

0x-Professor/Agent-Skills-Hub · 36 tokens