trading-ops: Command for Claude Code

.claude/commands/ingest.md

ingest is a command for Claude Code from l3lackcurtains/trading-ops. It costs 22 tokens per session (2,611 once invoked), scanned A, original, MIT.

A controlled intake command for adding new framework knowledge to a project’s documentation and updating related guides. It accepts a file, web address, or short piece of text.

In plain words
What is it for?
Use it to add research or ideas to docs, classify whether they are new or existing knowledge, update guide material, and record the change in an ingest log.
Why use it?
It keeps documentation changes organized and makes sure proposed edits, cross-references, and link checks are reviewed before they are applied.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is l3lackcurtains/trading-ops's own configuration. It tells Claude Code how to work on trading-ops itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything trading-ops configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/validate_links.py.

Reuse

Borrowing it

Nothing to install: this file belongs to l3lackcurtains/trading-ops. 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/l3lackcurtains/trading-ops/main/.claude/commands/ingest.md
Clone the repo
git clone --depth 1 https://github.com/l3lackcurtains/trading-ops

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 ingest

README.md
[![agentmods](https://agentmods.dev/badge/commands/l3lackcurtains/trading-ops/ingest/github.svg)](https://agentmods.dev/commands/l3lackcurtains/trading-ops/ingest)
Your own site
<a href="https://agentmods.dev/commands/l3lackcurtains/trading-ops/ingest"><img src="https://agentmods.dev/badge/commands/l3lackcurtains/trading-ops/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.

agentmods 80×15 button for ingest

Your own site · 80×15
<a href="https://agentmods.dev/commands/l3lackcurtains/trading-ops/ingest"><img src="https://agentmods.dev/badge/commands/l3lackcurtains/trading-ops/ingest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,611 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 $0.00022 $0.02611
Opus 5 $0.00011 $0.01306
Sonnet 5 $0.00004 $0.00522
Haiku 4.5 $0.00002 $0.00261

Measured 9d ago against content hash 76bc20bc71e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 9d 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/commands/ingest.md · 204 lines

How it starts

The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ingest — knowledge intake + protocol recalibration

/ingest <source> is the single authorized writer inside docs/. Every other command, freeform action, scan, and the self-improvement loop treats docs/ as read-only. This command is the carve-out.

What it does

  1. Parse the source — file path / URL / inline text or idea
  2. Read or fetch the content
  3. Classify the knowledge — new framework doc · extension of existing doc · pure protocol/data-source change (which doesn't belong in docs/)
  4. Propose a write plan — what gets created/edited in docs/, what gets recalibrated in guide/, what cross-references update
  5. Apply only after user consent
  6. Run link validation
  7. Append an entry to docs/INGEST_LOG.md

Argument forms

Form Example Behavior
File path /ingest input/spotgamma-2026.pdf Read local file (PDF, MD, TXT). For PDFs, use the Read tool's pages param for files > 10 pages.
URL /ingest https://example.com/paper WebFetch the URL. Use chrome-devtools for dynamic pages.
Inline text or idea /ingest "Add dealer-positioning section to macro.md — when SPX gamma flips negative, dealers buy rallies and sell dips. Source: Nomura/McElligott." The argument itself is the knowledge to ingest
No args /ingest Show help + last 5 entries from docs/INGEST_LOG.md

Steps

Step 1 — Parse + classify the source

Determine:

  • Source type — file / URL / inline
  • Content domain — macro · long-term-investing · technical (VWAP/VP) · options/dealer flow · news-trading · new asset class · new tool/methodology
  • Scope — new doc · append to existing doc · cross-cutting (touches multiple docs)
  • Where it lands — does this create knowledge (docs/), or only change how we apply it (guide/)? If the latter, this is a self-improvement-loop change, not an /ingest. Don't write to docs/ if the change is purely procedural.

If the classification is ambiguous, ask the user before continuing.

Read the full file on GitHub · 204 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. 9d ago First seen · 204 lines · 22 tokens per session scan A 76bc20bc71e3

Subscribe to this mod's changes

ingest is a command published in the GitHub repository l3lackcurtains/trading-ops (56 stars, last pushed 4mo ago), licensed MIT. It adds 22 tokens to every session and 2,611 once invoked, about $0.0001 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.