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/nitishxyz/solforge/agents-mdgit clone --depth 1 https://github.com/nitishxyz/solforgeWhat 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 | $0.01793 | $0.01793 |
| Opus 5 | $0.00897 | $0.00897 |
| Sonnet 5 | $0.00359 | $0.00359 |
| Haiku 4.5 | $0.00179 | $0.00179 |
Grade A, and why
solforge 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 — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Development Guidelines for SolForge
Core Principles
1. Keep It Modular
- No huge files: If a file exceeds 200 lines, consider splitting it
- Single responsibility: Each module should do one thing well
- Clear boundaries: Well-defined interfaces between modules
2. Keep It Simple
- Straightforward code: Prefer clarity over cleverness
- Minimal abstractions: Only abstract when there's clear benefit
- Explicit over implicit: Make intentions clear in code
3. Keep It Fast
- Performance matters: This is a performance-critical tool
- Measure first: Profile before optimizing
- Memory conscious: Avoid unnecessary allocations
Technology Rules
Package Manager
- ALWAYS use Bun: No npm, yarn, pnpm, or anything else
- Commands:
bun install(not npm install)bun run(not npm run)bun test(not jest/vitest)bun build(not webpack/esbuild)
Runtime
- Bun exclusively: Use Bun-native APIs when available
- Prefer
Bun.serve()over Express - Use
Bun.file()overfs.readFile() - Use
bun:testfor testing
Code Style
File Naming
- kebab-case: All files use kebab-case
- ✅
rpc-server.ts - ✅
get-account-info.ts - ❌
rpcServer.ts - ❌
GetAccountInfo.ts
- ✅
Directory Structure
packages/server/src/
├── methods/
│ ├── account/ # When account.ts gets too big
│ │ ├── get-account-info.ts
│ │ ├── get-balance.ts
│ │ ├── get-multiple-accounts.ts
│ │ └── index.ts
│ ├── transaction/ # When transaction.ts gets too big
│ │ ├── send-transaction.ts
│ │ ├── simulate-transaction.ts
│ │ └── index.ts
│ └── index.ts
File Size Guidelines
- < 100 lines: Ideal file size
- 100-200 lines: Acceptable
- > 200 lines: Consider splitting
- > 300 lines: Must split
When to Split Files
If account.ts or transaction.ts grows large:
- Create a directory with the same name
- Split into individual method files
- Create an index.ts that exports everything
- Update imports to maintain compatibility
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 · 271 lines · 1,793 tokens per session scan A dac367c681ad
solforge AGENTS.md is an instructions file published in the GitHub repository nitishxyz/solforge (23 stars, last pushed 7mo ago), licensed MIT. It adds 1,793 tokens to every session, about $0.0090 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 2026-08-30.
Other instructions, from other repositories
pumpfun-bonkfun-bot CLAUDE.md
Instructions for chainstacklabs/pumpfun-bonkfun-bot, covering agent guide, ground rules, layout, naming inside learning-examples/ and commands.
safe_wallet AGENTS.md
Instructions for ascenx/safe_wallet, covering agents.md, 1. 沟通原则, 2. 工作方式, 3. 代码修改边界 and 4. git 规则.
orquestra copilot-instructions.md
Instructions for berkayoztunc/orquestra, covering copilot instructions — orquestra, project overview, architecture, key patterns & conventions and worker route structure.
core-ai CLAUDE.md
Instructions for helius-labs/core-ai, covering core ai, compiler-managed sync, mcp server pin, skill versioning and router surface maintenance.
core-ai AGENTS.md
Instructions for helius-labs/core-ai, covering core ai — agent instructions, repository overview, mcp server setup, api key setup and public tool surface.
x402-client AGENTS.md
Instructions for vybenetwork/x402-client, covering vybe x402 client — agent instructions, quick reference, prerequisites, complete flow and step 1: install.