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/withautonomi/saorsa-core/agents-mdgit clone --depth 1 https://github.com/WithAutonomi/saorsa-coreWrote 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/withautonomi/saorsa-core/agents-md)<a href="https://agentmods.dev/instructions/withautonomi/saorsa-core/agents-md"><img src="https://agentmods.dev/badge/instructions/withautonomi/saorsa-core/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 | $0.01145 | $0.01145 |
| Opus 5 | $0.00573 | $0.00573 |
| Sonnet 5 | $0.00229 | $0.00229 |
| Haiku 4.5 | $0.00114 | $0.00114 |
Grade A, and why
saorsa-core 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 5d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guidelines for Saorsa Core
DHT Phonebook + Trust Signals (Current Direction)
Core Responsibilities
- DHT is a peer phonebook only (peer records, routing, discovery).
- User data storage lives in saorsa-node via
send_message-style APIs. - Trust remains in saorsa-core: saorsa-node reports data availability outcomes so EigenTrust can downscore nodes that fail to serve expected data.
Trust Signal Hook (saorsa-node → saorsa-core)
use saorsa_core::adaptive::{EigenTrustEngine, NodeStatisticsUpdate};
// After a data fetch attempt in saorsa-node:
trust_engine
.update_node_stats(&peer_id, NodeStatisticsUpdate::CorrectResponse)
.await;
// or on failure:
trust_engine
.update_node_stats(&peer_id, NodeStatisticsUpdate::FailedResponse)
.await;
Build/Test Commands
- Build:
cargo build --all-features(release:cargo build --release) - Test All:
cargo test --all-features(doc tests:cargo test --doc) - Single Test:
cargo test test_function_nameorcargo test --test integration_test_name - Lint:
cargo clippy --all-features -- -D clippy::panic -D clippy::unwrap_used -D clippy::expect_used - Format:
cargo fmt --all -- --check(apply:cargo fmt --all) - Local CI:
./scripts/local_ci.sh(runs fmt, clippy, build, tests safely)
Code Style Guidelines
Error Handling (ZERO PANICS in production)
- NEVER use:
.unwrap(),.expect(),panic!()in library/production code - Use instead:
?operator,.ok_or(),.context()fromanyhow - Tests OK:
.unwrap()/.expect()allowed in#[cfg(test)]blocks - Error types:
P2PErrorenum with structured variants,thiserrorfor derives
Imports & Dependencies
- Core async:
tokio,futures,async-trait - Serialization:
serdewith derive features - Error handling:
anyhow,thiserror - Logging:
tracing(neverprintln!in production) - Crypto:
saorsa-pqc(primary),saorsa-transport(QUIC transport)
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.
- 5d ago First seen · 95 lines · 1,145 tokens per session scan A 4a6e786f4bac
saorsa-core AGENTS.md is an instructions file published in the GitHub repository WithAutonomi/saorsa-core (5 stars, last pushed today), licensed Apache-2.0. It adds 1,145 tokens to every session, about $0.0057 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
antseed CLAUDE.md
Claude Code instructions for AntSeed/antseed, covering claude.md -- agent context for antseed monorepo, commit & push policy (important), changelog policy for prs, project overview and repository structure.
antseed AGENTS.md
AGENTS.md instructions for AntSeed/antseed, a project described as: AntSeed P2P AI Network - An open market for AI inference. No gatekeepers.
iron AGENTS.md
AGENTS.md instructions for lucascherzer/iron, covering coding guidelines, tests, code style, project management and community skills.
iron copilot-instructions.md
Copilot instructions for lucascherzer/iron, a project described as: iron - P2P mesh network based on iroh.
start-technologies AGENTS.md
AGENTS.md instructions for Start9Labs/start-technologies, covering agents.md, layout, build & test (run from the repo root), branches and channels and releases.
kubefwd CLAUDE.md
Claude Code instructions for txn2/kubefwd, covering claude.md, project overview, integration and usage patterns, tui (terminal user interface) and tui features.