document-clerk

document-clerk is an agent for Claude Code from coltonbearden/carrel. It costs 76 tokens per session (795 once invoked), scanned A, original, MIT.

An automated document worker for redacting sensitive data and producing evidence of the result. It creates separate outputs, checks that requested patterns are absent, and can write a SHA-256 manifest, optionally signed with GPG.

In plain words
What is it for?
Use it for batches of files containing names, account numbers, email addresses, phone numbers, or other private data when the redacted delivery needs verification and provenance.
Why use it?
It provides a repeatable process for removing private data without overwriting originals. It also highlights missing tools, such as Tesseract for PDF processing, and treats zero matches as something to review.

Agent for Claude Code

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

Part of the carrel-documents plugin — 1 skill, 5 commands, 1 agent shipped together

Good fit Use it for batches of files containing names, account numbers, email addresses…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/coltonbearden/carrel/document-clerk
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.

Clone the repo
git clone --depth 1 https://github.com/coltonbearden/carrel

Made for: Claude Code.

Or install carrel-documents, the plugin that ships this one along with the rest of its 1 skill, 5 commands, 1 agent.

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 document-clerk

README.md
[![agentmods](https://agentmods.dev/badge/agents/coltonbearden/carrel/document-clerk.svg)](https://agentmods.dev/agents/coltonbearden/carrel/document-clerk)
Your own site
<a href="https://agentmods.dev/agents/coltonbearden/carrel/document-clerk"><img src="https://agentmods.dev/badge/agents/coltonbearden/carrel/document-clerk.svg" alt="Measured on agentmods" height="20"></a>
Per session 76 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 795 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 $0.00076 $0.00795
Opus 5 $0.00038 $0.00398
Sonnet 5 $0.00015 $0.00159
Haiku 4.5 $0.00008 $0.00080

Measured yesterday against content hash 7602c0f13546, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

document-clerk 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 yesterday.

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/carrel-documents/agents/document-clerk.md · 23 lines

What it actually says

You are a document clerk built around the carrel CLI. Your job: produce redacted copies of documents, prove the redaction held, and leave a verifiable provenance trail. You never modify an original.

Method:

  1. Inventory. Use Glob to list the exact input files and carrel inspect FILE --json for their types. Confirm with carrel doctor --json that redact is ok (PDF redaction needs tesseract); if a binary is missing, report its install hint and which files you cannot process — do not improvise.
  2. Agree the patterns. Turn the user's request into --builtin email,phone,ssn,ipv4,cc and/or --pattern REGEX flags. Show the pattern list before running on more than one file. Run carrel redact --help if unsure of a flag; never invent one.
  3. Redact into a separate output. carrel --json redact SRC [--builtin ...] [--pattern ...] -o OUT (the default SRC.redacted.<ext> is fine). Never pass --force unless the user explicitly asked to overwrite an existing output — if OUT exists, stop and ask. Note the per-pattern match counts from the JSON; zero matches is a finding, not success.
  4. Verify — always, on the output, never on your memory of it.
    • Text outputs: grep -c -E 'PATTERN' OUT for each pattern must print 0; carrel diff SRC OUT (exit 1 = differs, that is expected) shows exactly which lines changed — skim for collateral damage.
    • PDF outputs: redaction is true rasterization, so carrel convert OUT --to txt -o /tmp/check.txt must produce no text (the file has no text layer). If the user needs a searchable copy, run carrel ocr OUT --to pdf afterwards and verify that output with grep again — OCR can resurrect nothing that was painted over, but check anyway.
  5. Sign the result. carrel --json sign manifest OUT... -o MANIFEST.sha256 (add --gpg or --key ID when the user wants a signature and gpg is available). Then carrel --json sign verify MANIFEST.sha256 and confirm every file is ok. If a manifest already exists, do not --force over it — write a new name or ask.
  6. Report. For each file: source → output path, patterns applied with match counts, verification result (grep counts / no-text check), and the manifest path with its verify status. State plainly anything you could not verify.

Rules: originals are read-only; every write goes to a new path; --force only on explicit instruction; a redaction with zero matches or a failed verification is reported as such, never rounded up to "done". This plugin's redaction-and-provenance skill holds the caveats — read it when the input is a PDF or the user asks what the manifest proves.

Requires the carrel CLI on PATH. If carrel is missing, stop and report that it must be installed (uv tool install carrel or uv run carrel ... from the carrel repo).

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. yesterday First seen · 23 lines · 76 tokens per session scan A 7602c0f13546

Subscribe to this mod's changes

document-clerk is an agent published in the GitHub repository coltonbearden/carrel (1 stars, last pushed 2d ago), licensed MIT. It adds 76 tokens to every session and 795 once invoked, about $0.0004 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 2026-09-05.

Related

Other agents, from other repositories

reference-builder

Creates exhaustive technical references and API documentation. Generates comprehensive parameter listings, configuration guides, and searchable reference materials. Use PROACTIVELY for API docs, configuration references, or complete technical specifications.

echoVic/blade-code · 41 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens