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/shieldspprt/solhunt-recovery/agents-mdgit clone --depth 1 https://github.com/shieldspprt/solhunt-recoveryWrote 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/shieldspprt/solhunt-recovery/agents-md)<a href="https://agentmods.dev/instructions/shieldspprt/solhunt-recovery/agents-md"><img src="https://agentmods.dev/badge/instructions/shieldspprt/solhunt-recovery/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 5.1 | $0.01806 | $0.01806 |
| Opus 5 | $0.00903 | $0.00903 |
| Sonnet 5 | $0.00361 | $0.00361 |
| Haiku 4.5 | $0.00181 | $0.00181 |
Grade A, and why
solhunt-recovery 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SolHunt Recovery — Multi-Dimension Agent Guide
Four Dimensions
SolHunt operates across 4 distinct product surfaces. Each has its own stack, priorities, and improvement cadence. Every hourly run should cover at least 2 dimensions.
Dimension 1: SolHunt PWA (React Web App)
Path: /home/workspace/solhunt-recovery/
Stack: React 19 + Vite + TypeScript 5.9 strict + Tailwind CSS + Zustand + @solana/web3.js
Repo: shieldspprt/solhunt-recovery
9 Recovery Engines
Revoke, Reclaim Rent, Dust Consolidator, Staking Ticket Finder, LP Fee Harvester, Buffer Account Recovery, Decommission Scanner, cNFT Cleaner, MEV/Priority Fee Claims.
Priority Areas (PWA)
| Priority | Area | Status |
|---|---|---|
| HIGH | Input validation — remaining scanners | Open |
| HIGH | Type safety — remove any from catch blocks |
Open |
| MEDIUM | Performance — memoization + virtualisation | In progress |
| MEDIUM | Error handling — circuit breakers for external APIs | Open |
| LOW | Code quality — JSDoc, naming consistency | Open |
Key Files (PWA)
| Category | Files |
|---|---|
| Critical security | src/lib/transactionSender.ts, src/lib/validation.ts, src/lib/transactionVerifier.ts |
| Core RPC | src/lib/rpcRetry.ts, src/lib/scanner.ts |
| Engines | src/modules/*/lib/*.ts (orca, raydium, meteora, ticket, buffer, decommission) |
| Hooks | src/modules/*/hooks/use*Scanner.ts |
| UI components | src/components/, src/pages/ |
| PWA config | vite.config.ts, src/sw.ts, app/ (Android TWA) |
Compliance Archive ✅
| Requirement | Status | File |
|---|---|---|
| Wallet connect/disconnect | ✅ FIXED | WalletStatusManager.tsx |
| TX error handling + RPC retry | ✅ FIXED | rpcRetry.ts |
| Mobile deep links + TWA | ✅ FIXED | AndroidManifest.xml |
| Fee disclosure + consent flows | ✅ FIXED | All *ConfirmModal components |
| RPC retry hardening | ✅ FIXED | All scanner modules |
Dimension 2: SolHunt MCP Server (AI Agent Interface)
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 · 191 lines · 1,806 tokens per session scan A 59f53a143701
solhunt-recovery AGENTS.md is an instructions file published in the GitHub repository shieldspprt/solhunt-recovery (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,806 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 2026-08-31.
Other instructions, from other repositories
origin-dollar CLAUDE.md
Claude Code instructions for OriginProtocol/origin-dollar, covering claude.md, project overview, toolchain, setup and @oplabs/talos-client (private, optional).
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.
solana-com CLAUDE.md
Claude Code instructions for solana-foundation/solana-com, covering solana.com monorepo, monorepo structure, tech stack, development commands and install dependencies.
behavioral-prediction-mcp CLAUDE.md
Instructions for ChainAware/behavioral-prediction-mcp, covering chainaware behavioral prediction mcp, project overview, mcp tools (14 total), batch pipeline and repository structure.
ghostswap-agents AGENTS.md
Instructions for ghostswap1/ghostswap-agents, covering agents.md — ghostswap partners api agent guide, what the ghostswap partners api does, pick the right surface for your runtime, core flow — every integration looks like this and authentication.
rugcheck-ai AGENTS.md
AGENTS.md instructions for MrWizardlyLoaf/rugcheck-ai, covering rugcheck ai — agent guide, connect (no install), tools, source & stack and self-host.