Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/littlebearapps/pitchdocsnpx agentmods add skills/littlebearapps/pitchdocs/llms-txtWrote 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/skills/littlebearapps/pitchdocs/llms-txt)<a href="https://agentmods.dev/skills/littlebearapps/pitchdocs/llms-txt"><img src="https://agentmods.dev/badge/skills/littlebearapps/pitchdocs/llms-txt.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 5.1 | $0.00061 | $0.01771 |
| Opus 5 | $0.00030 | $0.00886 |
| Sonnet 5 | $0.00012 | $0.00354 |
| Haiku 4.5 | $0.00006 | $0.00177 |
Grade A, and why
llms-txt 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
llms.txt Generator
Generate structured, LLM-friendly content indexes following the llmstxt.org specification.
Background
llms.txt was proposed by Jeremy Howard (Answer.AI) in September 2024. It provides a curated Markdown file that gives LLMs a structured map of a project's most important content — solving the problem of context windows being too small to process entire websites or repositories.
Adopted by: Anthropic, Cloudflare, Stripe, Vercel, Cursor, Mintlify, GitBook, Fern.
Used by: Cursor, Windsurf, Context7 MCP, Claude Code (reading local files), AI search engines.
Specification (llmstxt.org)
An llms.txt file is a Markdown document with sections in this exact order:
- H1 heading (required) — the name of the project or site
- Blockquote (optional) — short summary with key information for understanding the rest of the file
- Body text (optional) — zero or more Markdown sections of any type except headings
- H2 sections with file lists (optional) — each contains a Markdown list where every item has:
- A required hyperlink:
[name](url) - Optionally a
:followed by notes about the file
- A required hyperlink:
## Optionalsection (special) — URLs here can be skipped when shorter context is needed
No other heading levels are used. Only H1 (one, at the top) and H2 (for sections).
Two Output Files
| File | Content | Size Target | Use Case |
|---|---|---|---|
llms.txt |
Index with links and descriptions | Under 10K tokens | Real-time AI assistants navigating quickly |
llms-full.txt |
Concatenated Markdown of all referenced files | Varies (can be 100K+ tokens) | RAG ingestion, IDE indexing, full-context tools |
Generation Workflow
Step 1: Gather Project Metadata
Read the primary manifest for the project name and description:
| File | Name Field | Description Field |
|---|---|---|
package.json |
name |
description |
pyproject.toml |
[project].name |
[project].description |
Cargo.toml |
[package].name |
[package].description |
go.mod |
module path | First line of README |
.claude-plugin/plugin.json |
name |
description |
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.
- 8d ago First seen · 208 lines · 61 tokens per session scan A ad79d5ab2dd2
llms-txt is a skill published in the GitHub repository littlebearapps/pitchdocs (8 stars, last pushed 4mo ago), licensed MIT. It adds 61 tokens to every session and 1,771 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.
Other skills, from other repositories
docs
Generate and update living documentation — tech docs, user guides, philosophy overview. Composable building block for CLOSE and other skills.
init-rpm
Project setup and verification. First run creates rpm context for a project. Repeat runs verify that an existing rpm setup matches the latest expected layout and apply safe migrations.
root-cause-first
A debugging discipline that requires finding the underlying cause of a bug before changing the code. It also sets rules for handling errors, fallbacks, retries, and temporary diagnostics.
refresh
Use when an existing contextualizer's references may have drifted from current upstream state — typically weekly, or whenever a few days of upstream changes have accumulated — to bring them back into agreement.
backlog
Manage the rpm backlog (long-term project tasks in docs/rpm/future/tasks.org — distinct from Claude's native TaskCreate list, which is session-scoped). Add, list, review, postpone, or complete entries. TRIGGER on natural-language backlog operations — phrasings like "backlog X", "add X to backlog", "add to backlog"…
using-skill-engine
When the user mentions skill-engine or "the engine" without naming a specific workflow, or wants first-run setup. Inspects .claude/skills/-context/ install state (and any pending -context.proposed/ proposals) across all three install levels, then dispatches to engine-bootstrap when no contextualizer exists, to…