What is approve_ingest?

A command for approving reviewed knowledge-import files and archiving them in a wiki’s processed folder. It also updates the wiki’s links and tracking details to match the new file locations.

Use it to process pending-review import batches, verify their wiki pages, record old and new paths, update processing dates and statuses, and repair links to the moved files.

It removes the manual work of moving approved files and finding references that still point to their old locations. It is intended to run only after the user confirms the import is correct.

approve_ingest — Command for Claude Code by songzhuozhu

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/songzhuozhu/obsidian-llm-wiki

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/commands/songzhuozhu/obsidian-llm-wiki/approve_ingest/github.svg)](https://agentmods.dev/commands/songzhuozhu/obsidian-llm-wiki/approve_ingest)

Your own site

<a href="https://agentmods.dev/commands/songzhuozhu/obsidian-llm-wiki/approve_ingest"><img src="https://agentmods.dev/badge/commands/songzhuozhu/obsidian-llm-wiki/approve_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/commands/songzhuozhu/obsidian-llm-wiki/approve_ingest"><img src="https://agentmods.dev/badge/commands/songzhuozhu/obsidian-llm-wiki/approve_ingest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 535 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	$0.00031	$0.00535
Opus 5	$0.00015	$0.00267
Sonnet 5	$0.00006	$0.00107
Haiku 4.5	$0.00003	$0.00053

Measured 12d ago against content hash 6b335072de07, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

approve_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 12d 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.

.claude-en/commands/approve_ingest.md · 48 lines

What it actually says

Command: approve_ingest

You are the knowledge-maintenance agent for inspool-wiki-en/. Follow inspool-wiki-en/AGENTS.md strictly.

Task for this run: after the user has explicitly confirmed that the ingest result is correct, archive the corresponding pending_review ingest unit into inspool-wiki-en/raw/processed/.

Execute in this order:

Read inspool-wiki-en/AGENTS.md.
Review inspool-wiki-en/raw/index.md and inspool-wiki-en/wiki/log.md.
Scan inspool-wiki-en/raw/unprocessed/.
Find ingest units currently marked pending_review.
If the user specified a batch, process that batch. Otherwise, prioritize the most recently updated pending_review batch.
Verify that the corresponding wiki pages and processed_into fields exist.
Record the old and new path for every raw file in that ingest unit.
Update workflow fields for each raw file, for example:
- processing_status: processed
- reviewed_at: <today>
- processed_at: <today>
Move those raw files into inspool-wiki-en/raw/processed/.
Repair old raw references in source pages and other wiki pages, including at minimum:

raw_note in frontmatter
the "raw material" link under source information
any other hard-coded raw/unprocessed/... path strings

Run a localized self-check to confirm that inspool-wiki-en/wiki/ no longer contains those old paths.
Update inspool-wiki-en/raw/index.md.
Append an approve log entry to inspool-wiki-en/wiki/log.md.

Constraints:

run this flow only after explicit user approval
do not substantially rewrite wiki prose during approval
you must repair path references broken by raw-file movement
if the path self-check fails, report the remaining stale paths explicitly instead of silently treating the archive as successful
if the pending_review batch does not match existing wiki records, report the mismatch before taking action

Output requirements:

state which ingest unit you are archiving
list which raw files moved into processed/
state clearly whether the stale-path check passed
if archiving was blocked, explain why

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.

12d ago First seen · 48 lines · 31 tokens per session scan A 6b335072de07

Subscribe to this mod's changes

approve_ingest is a command published in the GitHub repository songzhuozhu/obsidian-llm-wiki (121 stars, last pushed 4mo ago), licensed MIT. It adds 31 tokens to every session and 535 once invoked, about $0.0002 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.

approve_ingest

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Command: approve_ingest

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

converge

implement

analyze