pdf-to-md-fixer

pdf-to-md-fixer is an agent for Claude Code from wahidyankf/ose-public. It costs 36 tokens per session (907 once invoked), scanned A, original, MIT.

A PDF-to-Markdown repair agent that rechecks reported differences against the original PDF and current Markdown, then restores confirmed content from the source. It records false positives and uncertain repairs.

In plain words
What is it for?
Use it to fix confirmed missing or inaccurate text, tables, figures, and other fidelity gaps in Markdown converted from a PDF.
Why use it?
It avoids repairing a conversion from memory or from an outdated copy, which could introduce new errors or overwrite valid changes.

Agent for Claude Code

Written for Claude Code: when-to-use in frontmatter. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to fix confirmed missing or inaccurate text, tables, figures, and other fidelity gaps in Markdown converted from a PDF.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/wahidyankf/ose-public/pdf-to-md-fixer
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/wahidyankf/ose-public

Made for: Claude Code.

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 pdf-to-md-fixer

README.md
[![agentmods](https://agentmods.dev/badge/agents/wahidyankf/ose-public/pdf-to-md-fixer/github.svg)](https://agentmods.dev/agents/wahidyankf/ose-public/pdf-to-md-fixer)
Your own site
<a href="https://agentmods.dev/agents/wahidyankf/ose-public/pdf-to-md-fixer"><img src="https://agentmods.dev/badge/agents/wahidyankf/ose-public/pdf-to-md-fixer/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 pdf-to-md-fixer

Your own site · 80×15
<a href="https://agentmods.dev/agents/wahidyankf/ose-public/pdf-to-md-fixer"><img src="https://agentmods.dev/badge/agents/wahidyankf/ose-public/pdf-to-md-fixer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 907 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 $0.00036 $0.00907
Opus 5.5 $0.00014 $0.00363
Sonnet 5.5 $0.00007 $0.00181
Haiku 4.5 $0.00004 $0.00091

Measured 2d ago against content hash e53f3fc185cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pdf-to-md-fixer 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 2d 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.

.agents/agents/pdf-to-md-fixer.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PDF to Markdown Fixer

Closes confirmed fidelity gaps from the source, never from memory.

Sole Writer

It executes PDF to Markdown Propagation, the pdf-to-md family's sole writer under Sole-Writer Propagation: it repairs only the rows of a frozen ledger, or rows an explicit request names, and each disposition below becomes the row's ledger status, as Applying Maker, Checker, and Fixer maps it. It never commits, starts a gate, or runs another propagation.

Inputs

  • findings (required): the check's returned findings or its recorded report.
  • pdf-file and md-file (optional): taken from the findings when omitted.
  • mode (optional): the lowest criticality the caller's loop counts. Default: every finding.
  • delegated-checks (optional): generic Markdown checks a gate owns for this file, each with its evidence.

Responsibility

  1. Open a fix report naming the check it answers, as Generating Validation Reports describes.
  2. Take findings in priority order. For each, extract the named source page again and re-read the copy at the named location, since the copy may have changed after the check.
  3. Rate confidence one finding at a time, applying the downgrades Converting PDF to Markdown lists for repairs that spread.
  4. Apply each HIGH repair as a targeted edit: restore text from the re-extracted page, correct a cell, move a heading or list to its source depth, fix a diagram's syntax without redesigning it, or add a placeholder for a figure left unrepresented. Read the span again after each edit.
  5. Record each FALSE_POSITIVE with what disproved it, so the next check does not raise it again, and each MEDIUM for a person.
  6. Close the report with the sections changed, so the next check can concentrate on them, and return delegated checks unrun: evidence for each whose scope intersects a changed section becomes pending, and the rest returns unchanged, as CI Quality Gate sets for edited files.

Read the full file on GitHub · 79 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. 2d ago First seen · 79 lines · 36 tokens per session scan A e53f3fc185cb

Subscribe to this mod's changes

pdf-to-md-fixer is an agent published in the GitHub repository wahidyankf/ose-public (12 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 907 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-14.

Related

Other agents, from other repositories

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

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 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

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

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