context-ingestion

context-ingestion is a skill for Claude Code, Codex from DojoGenesis/mcp. It costs 43 tokens per session (1,751 once invoked), scanned A, original, MIT.

A planning method that uses uploaded files—such as specifications, documentation, code, research, or images—as the basis for recommendations.

In plain words
What is it for?
Use it to create plans from files, plan code refactors, or turn meeting notes and design materials into specific action items.
Why use it?
It keeps plans tied to the actual project materials, while making constraints and contradictions visible instead of guessing around them.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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/dojogenesis/mcp/context-ingestion
Any agent
npx skills add DojoGenesis/mcp --skill context-ingestion
Clone the repo
git clone --depth 1 https://github.com/DojoGenesis/mcp

Made for: Claude Code, Codex.

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 context-ingestion

README.md
[![agentmods](https://agentmods.dev/badge/skills/dojogenesis/mcp/context-ingestion.svg)](https://agentmods.dev/skills/dojogenesis/mcp/context-ingestion)
Your own site
<a href="https://agentmods.dev/skills/dojogenesis/mcp/context-ingestion"><img src="https://agentmods.dev/badge/skills/dojogenesis/mcp/context-ingestion.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,751 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.01751
Opus 5 $0.00022 $0.00875
Sonnet 5 $0.00009 $0.00350
Haiku 4.5 $0.00004 $0.00175

Measured 6d ago against content hash b5ce4c665f6d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

context-ingestion 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 6d 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.

internal/skills/bundled/specification-driven-development/context-ingestion/SKILL.md · 221 lines

How it starts

The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context Ingestion Skill

Version: 1.0 Author: Tres Pies Design Purpose: Create plans that are deeply informed by uploaded content, ensuring that recommendations are specific, actionable, and aligned with the provided context. Includes intent-based routing for automatic mode selection.


I. The Philosophy: Grounding is Everything

The quality of a plan is directly proportional to how well it is grounded in the available context. This skill transforms file uploads from passive attachments into active participants in the planning process, ensuring that every recommendation is rooted in the specifics of the provided files.

Core principles:

  • Every recommendation must reference a specific file, function, or section
  • Constraints found in files must be listed explicitly
  • Contradictions between files must be flagged, not silently resolved
  • Plans must be actionable without needing additional context

II. When to Use This Skill

  • When you have 1-2 files and a general planning request (e.g., "create a plan from this spec")
  • When you need to refactor a codebase and have uploaded the relevant files
  • When you want to create action items from meeting notes or a design document
  • When the intent-based router selects this mode
  • As the default mode when file types or intent are ambiguous

III. Intent-Based Routing

Before executing the context ingestion workflow, analyze the user's request to determine if another mode is a better fit.

Routing Table

File Types & Quantity Intent Keywords Selected Mode
1-2 files (any type) "plan", "refactor", "next steps", "action items" Context Ingestion (this skill)
Spec, requirements doc "spec", "prompt", "implement" Route to /write-spec or /write-prompt
3+ research files "synthesize", "research", "patterns", "compare" Research Synthesis
Ambiguous (default) Context Ingestion (this skill)

Routing Behavior

  • If routing to another command: Explain the routing decision and hand off. Example: "You uploaded a spec file and asked for an implementation prompt — routing to /write-prompt."
  • If staying in context ingestion: Proceed with the 5-step workflow below.
  • User override: If the router picks the wrong mode, the user can invoke the correct command directly.

Read the full file on GitHub · 221 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. 6d ago First seen · 221 lines · 43 tokens per session scan A b5ce4c665f6d

Subscribe to this mod's changes

context-ingestion is a skill published in the GitHub repository DojoGenesis/mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 1,751 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 2026-08-31.