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.
npx agentmods add instructions/losiochico/mdingest/agents-mdgit clone --depth 1 https://github.com/LOsioChico/mdingestWrote 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.
[](https://agentmods.dev/instructions/losiochico/mdingest/agents-md)<a href="https://agentmods.dev/instructions/losiochico/mdingest/agents-md"><img src="https://agentmods.dev/badge/instructions/losiochico/mdingest/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.09416 | $0.09416 |
| Opus 5 | $0.04708 | $0.04708 |
| Sonnet 5 | $0.01883 | $0.01883 |
| Haiku 4.5 | $0.00942 | $0.00942 |
Grade A, and why
mdingest AGENTS.md scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
### curl first, code second (G13) How it starts
The opening of the file, as written. The whole thing — 590 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — mdingest Operating Contract
API that ingests blog/article/newsletter pages to clean Markdown for LLM consumption. Currently supports Medium (via Freedium), Dev.to (via Forem API), and Substack (free posts via public API + HTML→Markdown). Designed for future providers.
Operating contract for any AI agent (Devin, Claude Code, Cursor) working on this repo. Read this file before writing code.
Communication style
- Lead with the next action. First line is something the reader can do.
- Number multi-step tasks. Each step is one bounded action.
- End with one concrete next step.
- Suppress tangents. Finish the first issue, then offer the second.
- Restate state every turn. One-line status before the new action.
- Specific time estimates. "About 15 minutes if tests cover this" — not "a bit".
- Make wins visible. When something works, say so with evidence.
- Matter-of-fact errors. State cause and fix. No "Uh oh" or "Oh no".
- Cap lists at 5 items. Group into sub-lists or split into steps if longer.
- No preamble, no recap, no closers.
Code style
- Named exports only. No default exports. Greppable, explicit imports.
- Short files. One responsibility per file. If a file exceeds ~150 lines, split it.
- Tables over paragraphs in docs and comments. Scannable, not readable.
- Flat folder structure. Max 2 levels deep under
src/. - File names say what's inside.
freedium.service.tsfetches from Freedium. Noutils.ts. - No walls of text in comments. If a comment exceeds 3 lines, it's a doc — move it to
docs/. - Functional style: pure functions where possible, no classes except NestJS modules/services/controllers.
- Use TypeScript features: type narrowing, discriminated unions,
satisfies,as const.
Terminology
This project uses ingest terminology, not "convert":
| Term | Use | Don't use |
|---|---|---|
| Feature name | ingest | convert |
| UI component | Ingestor.tsx |
Converter.tsx |
| Route | /ingest |
/convert |
| Function | handleIngest |
handleConvert |
| Result type | IngestResult |
ConvertResult |
| CSS class | ingestor-* |
converter-* |
| Button text | "Ingest" | "Convert" |
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.
- 4d ago First seen · 590 lines · 9,416 tokens per session scan A 333ac79726d9
mdingest AGENTS.md is an instructions file published in the GitHub repository LOsioChico/mdingest (1 stars, last pushed 5d ago), licensed MIT. It adds 9,416 tokens to every session, about $0.0471 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
oh-my-pi AGENTS.md
AGENTS.md instructions for can1357/oh-my-pi, covering development rules, default context, package structure, github and code quality.
gini-agent AGENTS.md
AGENTS.md instructions for Open-Curiosity/gini-agent, covering gini agent instructions, shape, adrs, boundaries and branches.
gno AGENTS.md
AGENTS.md instructions for gmickel/gno, covering knowledge cutoff warning, apis - bun first!, must use bun, acceptable node:\ (no bun equivalent) and testing.
sixb AGENTS.md
AGENTS.md instructions for sixb-ai/sixb, covering agents.md, scope, repo map, toolchain and core commands.
web-researcher-mcp CLAUDE.md
Claude Code instructions for zoharbabin/web-researcher-mcp, covering claude.md — web-researcher-mcp, commands, contribution rules, architecture and non-obvious top-level dirs.
tinycode AGENTS.md
AGENTS.md instructions for bobbyjohnstx/tinycode, covering commits and pr titles, style guide, general principles, destructuring and variables.