A workflow for turning files placed in an inbox folder into Markdown documents stored in a workmemory folder. It uses a document-conversion tool, keeps the original folder structure, and adds information about each source file and conversion time.

Use it to add new documents to a local knowledge base or refresh existing ones. It can scan the inbox recursively, convert supported files, and optionally force a full refresh.

It turns mixed local source files into a consistent, searchable knowledge-base format. It also continues when one file fails and reports what was converted, skipped, or unsuccessful.

How haxudev/personal_kb configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to haxudev/personal_kb. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/haxudev/personal_kb/main/.github/skills/ingest/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/haxudev/personal_kb

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/haxudev/personal_kb/ingest/github.svg)](https://agentmods.dev/skills/haxudev/personal_kb/ingest)

Your own site

<a href="https://agentmods.dev/skills/haxudev/personal_kb/ingest"><img src="https://agentmods.dev/badge/skills/haxudev/personal_kb/ingest/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/haxudev/personal_kb/ingest"><img src="https://agentmods.dev/badge/skills/haxudev/personal_kb/ingest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 336 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.

Model	Per session	Once invoked
Fable 5.1	$0.00033	$0.00336
Opus 5.5	$0.00013	$0.00134
Sonnet 5.5	$0.00007	$0.00067
Haiku 4.5	$0.00003	$0.00034

Measured 2mo ago against content hash a5f7cd9bcdda, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ingest 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 2mo 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.

.github/skills/ingest/SKILL.md · 51 lines

What it actually says

Skill: ingest

Use this skill when the user wants to add or refresh local knowledge.

Process

Detect the execution environment first:
- Windows CMD / PowerShell: prefer Windows-style commands
- macOS / Linux / WSL: use POSIX commands
Run python scripts/preflight.py to verify required dependencies.
Run the ingest script using the environment-appropriate Python launcher.
If the user requests a full refresh, append --force.
Report how many files were converted, skipped, or failed.

Environment-specific command preference

Windows CMD (preferred on Windows)

python scripts\preflight.py
python scripts\ingest.py
python scripts\ingest.py --force

Windows PowerShell

python .\scripts\preflight.py
python .\scripts\ingest.py
python .\scripts\ingest.py --force

macOS / Linux / WSL

python scripts/preflight.py
python scripts/ingest.py
python scripts/ingest.py --force

Expected behavior

Scan inbox/ recursively.
Convert supported files via markitdown.
Preserve relative paths under workmemory/.
Add YAML frontmatter containing source_path and ingested_at.
Continue past single-file failures and summarize them.

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.

2mo ago First seen · 51 lines · 33 tokens per session scan A a5f7cd9bcdda

Subscribe to this mod's changes

ingest is a skill published in the GitHub repository haxudev/personal_kb (2 stars, last pushed 6mo ago), licensed MIT. It adds 33 tokens to every session and 336 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 2026-08-31.

Documents

ingest next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ingesthaxudev/personal_kb	Skill	2	6mo ago	MIT	A	33	Claude Code
orbit-notionnexu-io/open-design	Skill	106k	yesterday	Apache-2.0	A	117	Claude Code, Codex
instrument-data-to-allotropeanthropics/knowledge-work-plugins	Skill	35k	2d ago	Apache-2.0	A	123	Claude Code
apify-youtube-transcript-scrapersickn33/agentic-awesome-skills	Skill	49k	yesterday	MIT	A	48	Claude Code
legal-holdanthropics/claude-for-legal	Skill	9.9k	3d ago	Apache-2.0	A	68	Claude Code
ppt-reviewOrkas-AI/Orkas	Skill	9.0k	today	MIT	A	2	Claude Code, Codex
feishuHmbown/CodeWhale	Skill	41k	5d ago	MIT	A	33	Claude Code, Codex

personal_kb: Skill for Claude Code