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/hirama/solidity-agentic-stack/claude-mdgit clone --depth 1 https://github.com/Hirama/solidity-agentic-stackWhat 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 | $0.00936 | $0.00936 |
| Opus 5 | $0.00468 | $0.00468 |
| Sonnet 5 | $0.00187 | $0.00187 |
| Haiku 4.5 | $0.00094 | $0.00094 |
Grade A, and why
solidity-agentic-stack CLAUDE.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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentic Stack for Solidity — CLAUDE.md
The Rule
Agents write. Tools verify. Humans sign.
- The agent may propose and write code. It never declares code correct — only the toolchain can.
- The toolchain (forge, slither, aderyn) is the authority. A green suite is the definition of done.
- The agent never broadcasts a transaction, never touches a private key, and never edits
.env.
Commands
# Build
forge build
# Format (check only — CI gate)
forge fmt --check
# Format (auto-fix)
forge fmt
# Unit + fuzz tests (default profile)
forge test
# Invariant tests only
forge test --match-contract VaultInvariant
# CI profile (higher fuzz/invariant runs)
FOUNDRY_PROFILE=ci forge test
# Coverage
forge coverage --report lcov
# Slither static analysis
slither .
# Aderyn static analysis
aderyn .
# Full definition-of-done gate
forge fmt --check && forge build && FOUNDRY_PROFILE=ci forge test && slither . && aderyn .
# Red team agent (requires ANTHROPIC_API_KEY)
python scripts/redteam.py --dry-run # print findings, no GitHub Issues
python scripts/redteam.py # print findings + file GitHub Issues
# Fix agent — patch a specific security issue (requires ANTHROPIC_API_KEY)
python scripts/fix.py --issue 42 --dry-run # apply fix locally, skip PR
python scripts/fix.py --issue 42 # fix + forge test + open PR
Invariants — The Constitution
These invariants MUST hold at all times. Never weaken an invariant to make a test pass. If an invariant breaks, the protocol is broken — fix the code, not the test.
| ID | Statement |
|---|---|
| INV-1 | address(vault).balance == vault.totalDeposits() |
| INV-2 | ghost_totalDeposited - ghost_totalWithdrawn == vault.totalDeposits() |
Hard Rules
Code quality
- CEI everywhere. Checks → Effects → Interactions. No exceptions.
- Custom errors only. No
requirestrings. Never revert with a bare string. - Named imports.
import {Foo} from "bar/Foo.sol"— no wildcard imports. - Full NatSpec on every public/external function and error.
- No
tx.originauth, noblock.timestampas randomness, no unbounded loops.
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 · 121 lines · 936 tokens per session scan A f921d13cf748
solidity-agentic-stack CLAUDE.md is an instructions file published in the GitHub repository Hirama/solidity-agentic-stack (5 stars, last pushed 2mo ago), licensed MIT. It adds 936 tokens to every session, about $0.0047 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
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.
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).
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.