A skill that fetches approved sources, keeps raw copies, and compiles them into structured Grimoire wiki articles. A Grimoire is a maintained knowledge wiki organised according to a project schema.

For processing approved URLs, local files, or pasted text, creating source archives, and compiling articles with metadata and links to related content.

It turns selected source material into consistent wiki content while preserving the original text for checking and later reference.

ingest — Skill for Claude Code and Codex by vedantggwp: A skill that fetches approved sources, keeps raw copies…

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.

agentmods

npx agentmods add skills/vedantggwp/grimoire/ingest

Any agent

npx skills add vedantggwp/grimoire --skill ingest

Clone the repo

git clone --depth 1 https://github.com/vedantggwp/grimoire

Made for: Claude Code, Codex.

Or install grimoire, the plugin that ships this one along with the rest of its 8 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/vedantggwp/grimoire/ingest.svg)](https://agentmods.dev/skills/vedantggwp/grimoire/ingest)

Your own site

<a href="https://agentmods.dev/skills/vedantggwp/grimoire/ingest"><img src="https://agentmods.dev/badge/skills/vedantggwp/grimoire/ingest.svg" alt="Measured on agentmods" height="20"></a>

Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,232 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00070	$0.03232
Opus 5	$0.00035	$0.01616
Sonnet 5	$0.00014	$0.00646
Haiku 4.5	$0.00007	$0.00323

Measured 5d ago against content hash 797cbbd5c684, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 5d 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.

skills/ingest/SKILL.md · 300 lines

How it starts

The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ingest

Fetch approved sources, preserve raw text, and compile structured wiki articles with frontmatter and cross-references.

Prerequisites

A grimoire workspace must exist — check for SCHEMA.md in the workspace root. If it is missing, tell the user to run /grimoire:new first.
Either approved-sources.md exists in the workspace (produced by scout), OR the user provides a direct source (URL, local file path, or pasted text).
Read SCHEMA.md before doing anything else — it defines the taxonomy, naming conventions, and confidence tiers that govern every output.

Step 1 — Identify the Source

Check for approved-sources.md in the workspace root.

If it exists, find the next source with status: pending. Pick the highest priority first (P0 before P1 before P2). Announce which source you are about to process and its tier.
If no approved-sources.md exists, accept a direct source from the user: a URL, a local file path, or pasted text. Ask if none has been provided.
If the user says "ingest all" or similar, do not batch silently. Process one source at a time in priority order. After completing Step 7 for each source, print the summary and ask: "Process the next source? ({N} remaining, next: {title})" before continuing.
Batch mode (orchestrated flow): When invoked as part of /grimoire:run or when the user explicitly requests batch processing ("ingest all sources without asking", "batch ingest", "process everything"), process all pending sources in priority order without per-source confirmation. For each source: fetch raw (Step 2), extract takeaways (Step 3), write articles using best judgment (Step 5), and update source status (Step 7) — skipping Step 4's human checkpoint. After ALL sources are processed, print a single summary:
```
Batch ingest complete: {N} sources processed.
  Created: {slugs}
  Updated: {slugs}
  Failed:  {slugs with reasons}
  Backlinks added: {N}
```
Then run Step 6 (update navigators) once for the full batch. If any source fails to fetch, mark it as failed and continue with remaining sources.

Read the full file on GitHub · 300 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.

references/stage-contract.md 1.8 KB

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.

5d ago First seen · 300 lines · 70 tokens per session scan A 797cbbd5c684

Subscribe to this mod's changes

ingest is a skill published in the GitHub repository vedantggwp/grimoire (2 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 3,232 once invoked, about $0.0003 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 2026-08-31.

LLM Research Writing and docs agent-tools claude-code knowledge-base local-first mcp

linkly-ai

Search, browse, read, and take notes across the user's documents indexed by Linkly AI — local files and linked cloud libraries. Use when the user asks to 'search my documents', 'find files about a topic', 'read a local document', 'what's in this folder', 'list the files in that library', 'browse document outlines'…

LinklyAI/linkly-ai-skills · 221 tokens

ingest

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

ingest

Prerequisites

Step 1 — Identify the Source

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

linkly-ai

vault-for-llm

memobase

dws

package-author

notes