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/statico/quickrag/agents-mdgit clone --depth 1 https://github.com/statico/quickragWhat 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 | $0.00633 | $0.00633 |
| Opus 5 | $0.00316 | $0.00316 |
| Sonnet 5 | $0.00127 | $0.00127 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
quickrag AGENTS.md 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 2d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QuickRAG
Keep this file brief and concise. Remove redundant information and condense verbose sections.
Releasing
- Update version:
npm version <major|minor|patch> --no-git-tag-version - Commit and tag:
git add package.json && git commit -m "vX.Y.Z" && git tag vX.Y.Z - Push:
git push && git push origin vX.Y.Z - Add release notes:
gh release edit vX.Y.Z --notes "..."(summarize changes since last version)
Code Style
- Keep code brief and concise
- Minimize comments - code should be self-explanatory
- Use official npm packages, not local references
Testing with test/ Data
The test directory contains sample documents for testing. Use the test config file to ensure consistent testing.
Setup
- Ensure Ollama is running with
nomic-embed-textmodel available - The test config is at
test/config.yaml(defaults to ollama)
Basic Test Commands
Index test data (with timing):
time bun run src/index.ts index test/ --config test/config.yaml --clear
Query the indexed data:
time bun run src/index.ts query index.rag "who is sherlock holmes" --config test/config.yaml
time bun run src/index.ts query index.rag "what is frankenstein" --config test/config.yaml
Test deduplication (with timing):
# First index
time bun run src/index.ts index test/ --config test/config.yaml --clear
# Index again (should skip existing chunks - should be very fast)
time bun run src/index.ts index test/ --config test/config.yaml
# Modify a file and re-index (should only index new chunks)
echo "test" >> test/sherlock-holmes.txt
time bun run src/index.ts index test/ --config test/config.yaml
git checkout test/sherlock-holmes.txt # restore file
Performance Testing
Compare indexing performance:
# Full index (should show batch counts and timing)
time bun run src/index.ts index test/ --config test/config.yaml --clear
# Re-index (should be fast, skipping existing chunks)
time bun run src/index.ts index test/ --config test/config.yaml
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.
- 2d ago First seen · 73 lines · 633 tokens per session scan A 7ce2c6f1f011
quickrag AGENTS.md is an instructions file published in the GitHub repository statico/quickrag (5 stars, last pushed 7mo ago), licensed Unlicense. It adds 633 tokens to every session, about $0.0032 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 instructions, from other repositories
RAGBuddy AGENTS.md
AGENTS.md instructions for azmirizkifar20/RAGBuddy, covering skills auto-load, documentation structure, knowledge retrieval strategy (ragbuddy mcp) and project status.
fff AGENTS.md
AGENTS.md instructions for dmtrKovalenko/fff, covering to clankers, development commands, building, testing and development tools and code quality.
GPT-RAG release.instructions.md
Instructions for Azure/GPT-RAG, a project described as: Sharing the learning along the way we been gathering to enable Azure OpenAI at enterprise scale in a secure manner. GPT-RAG core is a Retrieval-Augmented Generation pattern running in Azure, using Azure Cognitive Search for retrieval and Azure OpenAI large…
pi-coding-agent-forge AGENTS.md
Instructions for Firstp1ck/pi-coding-agent-forge, covering repository documentation rules, documentation goal, required documentation layers, readme.md — human guide and technical.md — advanced user reference.
rag-code-mcp copilot-instructions.md
Instructions for doITmagic/rag-code-mcp, covering copilot instructions - ragcode mcp, ⚖️ the golden rule, project overview, architecture & patterns and developer workflows.
agentconfig.org AGENTS.md
Instructions for agentconfig/agentconfig.org, covering agent instructions for agentconfig.org, project overview, target audience, site structure and tech stack.