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/wonna-fi/saaga/agents-mdgit clone --depth 1 https://github.com/wonna-fi/saagaWrote 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/wonna-fi/saaga/agents-md)<a href="https://agentmods.dev/instructions/wonna-fi/saaga/agents-md"><img src="https://agentmods.dev/badge/instructions/wonna-fi/saaga/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 | $0.00417 | $0.00417 |
| Opus 5 | $0.00209 | $0.00209 |
| Sonnet 5 | $0.00083 | $0.00083 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
saaga 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 today.
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.
What it actually says
Development Rules
Definition of Done Checklist
A task is ready when the following criteria are met:
- The implementation fulfills the requirements
- The implementation has tests
- The complete test suite passes
- There are no linter errors
Domain Documentation (saaga)
This codebase has structured domain documentation under saaga-docs/, organized into four types:
| Type | Index | Answers |
|---|---|---|
| Concepts | saaga-docs/concepts/INDEX.md |
What something is and where it lives |
| Patterns | saaga-docs/patterns/INDEX.md |
How to do common operations — anything that takes reading a code flow to follow |
| Conventions | saaga-docs/conventions/INDEX.md |
What things must be named or shaped like — the rules you could check with grep |
| Features | saaga-docs/features/INDEX.md |
How a feature works end-to-end, user-facing or internal machinery |
Classify your question, open the matching INDEX.md, and read the relevant document(s):
- "What is X / where does X live?" -> read a concept
- "How do I do X?" -> read a pattern
- "What do I call X / where does the file go?" -> read a convention
- "How does feature X work end-to-end?" -> read a feature
Not every codebase has conventions; the category is present only when there are rules worth stating.
Rules:
- Docs first: ALWAYS read the domain documentation BEFORE exploring source code. It is the authoritative source for understanding the system; source code is the second resort.
- No documentation updates during implementation: do NOT update the domain documentation when making code changes. It is maintained separately by Saaga.
- Consult before implementing: before implementing new features or changes, check the existing concepts and patterns to reuse existing services/modules instead of reinventing them.
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.
- today Changed · -1 lines · -114 tokens per session 7a16f61fcd41
- 4d ago First seen · 40 lines · 531 tokens per session scan A 9da130ca49aa
saaga AGENTS.md is an instructions file published in the GitHub repository wonna-fi/saaga (5 stars, last pushed yesterday), licensed MIT. It adds 417 tokens to every session, about $0.0021 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
evmole AGENTS.md
Instructions for cdump/evmole: EVMole extracts structured facts from deployed EVM runtime bytecode.
experiencer CLAUDE.md
Claude Code instructions for vincentlaucsb/experiencer: The canonical repository instructions are in AGENTS.md. Read and follow that file; this compatibility entrypoint intentionally defines no independent rules.
pip-web CLAUDE.md
Claude Code instructions for playpip/pip-web, covering claude.md — agent guide for pip, read first (by task), the three layers (respect the boundaries), non-negotiables and commands / definition of done.
bray AGENTS.md
AGENTS.md instructions for forgesworn/bray, covering agents.md — nostr-bray, what this is, build & test, architecture and tool groups.
bitcoin-mcp copilot-instructions.md
Instructions for Bortlesboat/bitcoin-mcp, covering bitcoin-mcp copilot instructions, rules, satoshi api reference and verification.
drpc-agent-skills GEMINI.md
Gemini CLI instructions for drpcorg/drpc-agent-skills: @./skills/drpc-rpc/SKILL.md @./skills/drpc-rpc/setup.md @./skills/drpc-rpc/direct-http.md @./skills/drpc-rpc/tools-reference.md @./skills/drpc-rpc/recipes-simple.md @./skills/drpc-rpc/recipes-crosschain.md @./skills/drpc-rpc/recipes-defi-basics.md…