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/allora-network/allora-chain/agents-mdgit clone --depth 1 https://github.com/allora-network/allora-chainWrote 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/allora-network/allora-chain/agents-md)<a href="https://agentmods.dev/instructions/allora-network/allora-chain/agents-md"><img src="https://agentmods.dev/badge/instructions/allora-network/allora-chain/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 | $0.01361 | $0.01361 |
| Opus 5 | $0.00681 | $0.00681 |
| Sonnet 5 | $0.00272 | $0.00272 |
| Haiku 4.5 | $0.00136 | $0.00136 |
Grade C, and why
allora-chain AGENTS.md scanned grade C 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 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.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
1. **Verify the signing key is available**: Run `ssh-add -l` and confirm the configured signing key is listed. If the agent has no identities or the key is missing, **stop immediately** and tell the user to load the key Copies of this mod
1 near-identical copy found in the catalogue:
- allora-chain CLAUDE.md — 98% identical, 5 lines differ
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Short, high-signal guidance for working in the allora-chain repo. Keep context small and only load extra docs when needed.
Quick Rules (Apply To Most Changes)
- Determinism: no
time.Now()/rand, no map-order dependence, no floats in consensus; usealloraMath.Dec/sdk.Int/sdk.Decand stable iteration. - State access: keepers are the only state access point; no IO, goroutines, or non-determinism inside keepers.
- Validation:
ValidateBasic+ keeper stateful checks; usesdkerrors/errorsmodfor typed errors. - Events: emit events for all state transitions with consistent type/attribute keys.
- Protos: never change field numbers; add new optional fields; use
Request/Responsefor list queries; new versions for breaking changes. - State layout: define keys/prefixes in
types/keys.go; keep prefix types stable; add indexes for query-heavy data. - Params/genesis: validate every param change + authority checks; genesis is deterministic with round-trip tests.
- Comments: self-contained; no issue/task IDs, PR/review links, or report names — describe the behavior, not the ticket. Applies to comments you copy or move during merges/rebases too. See
Code commentsbelow.
Go Conventions
- Always
gofmt/goimports;make lintmust always pass clean after producing complete code. Avoid usingnolintstatements if possible, but if you need to use it, add a comment on the reason why. - Prefer table-driven unit tests and explicit dependency injection for easy mocking.
- Use
sdk.Context.Logger()for chain logs; avoid noisy logs in consensus paths. - Only apply Allora Go Service patterns (brynbellomy errors, sqlc, viper, Gin, zerolog) if editing non-chain services.
Changes That Require Extra Steps
- Proto/state layout changes: add module migration + tests; bump
ConsensusVersionand wire upgrades if needed. - New module/store keys: update app wiring for store upgrades.
- Generated files (
*.pb.go,*.pulsar.go): never edit by hand; run codegen.
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 · 68 lines · 1,361 tokens per session scan C 9c408d34df1e
allora-chain AGENTS.md is an instructions file published in the GitHub repository allora-network/allora-chain (140 stars, last pushed 7d ago), licensed Apache-2.0. It adds 1,361 tokens to every session, about $0.0068 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.