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/zunmax/fhevm-skill/agents-mdgit clone --depth 1 https://github.com/zunmax/fhevm-skillWhat 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 | $0.03675 | $0.03675 |
| Opus 5 | $0.01837 | $0.01837 |
| Sonnet 5 | $0.00735 | $0.00735 |
| Haiku 4.5 | $0.00367 | $0.00367 |
Grade A, and why
fhevm-skill 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - FHEVM project guidance
This file is the project guidance loaded by AGENTS.md-aware coding agents (Codex CLI, Aider, Cline, Continue, Zed, Jules, etc.). It activates only when the project touches Zama FHEVM v0.11. If the project has no FHEVM imports, encrypted types, or FHEVM error strings, ignore this file.
Activation
Apply this file whenever you edit code that touches Zama FHEVM v0.11. Trigger conditions:
- Imports
@fhevm/solidity,@fhevm/hardhat-plugin,@fhevm/mock-utils,@zama-fhe/relayer-sdk(legacy primitives),@zama-fhe/sdk(new high-level SDK v3+),@zama-fhe/react-sdk(new React hooks v3+), or@openzeppelin/confidential-contracts. Sub-paths count:@zama-fhe/sdk/node,@zama-fhe/sdk/viem,@zama-fhe/sdk/ethers,@zama-fhe/sdk/cleartext,@zama-fhe/sdk/query,@zama-fhe/react-sdk/wagmi, plus the legacy@zama-fhe/relayer-sdk/web|bundle|node. - Declares or uses
euint8-euint256,ebool,eaddress,externalEuint*. - Contract inherits
ZamaEthereumConfig(the only current Solidity base), or any legacySepoliaConfig/MainnetConfigSolidity base from a pre-v0.9 codebase that needs migrating. (MainnetConfigandSepoliaConfigdo exist as TS exports in@zama-fhe/relayer-sdk/weband@zama-fhe/sdkfor frontend SDK config - those are unrelated to Solidity inheritance.) - Code uses any new-SDK identifier:
ZamaSDK,ZamaProvider,RelayerWeb,RelayerNode,RelayerCleartext,ViemSigner,EthersSigner,WagmiSigner,GenericSigner,Token,ReadonlyToken,WrappersRegistry,IndexedDBStorage,MemoryStorage,ChromeSessionStorage,matchZamaError,zamaQueryKeys,TOKEN_TOPICS,ACL_TOPICS; or any of the 59 React hooks (useShield,useUnshield,useUnshieldAll,useResumeUnshield,useConfidentialBalance,useConfidentialBalances,useConfidentialTransfer,useConfidentialTransferFrom,useConfidentialApprove,useConfidentialIsApproved,useAllow,useIsAllowed,useRevoke,useRevokeSession,useEncrypt,useUserDecrypt,usePublicDecrypt,useGenerateKeypair,useDelegateDecryption,useRevokeDelegation,useDelegationStatus,useDecryptBalanceAs,useBatchDecryptBalancesAs,useActivityFeed,useToken,useReadonlyToken,useMetadata,useUnderlyingAllowance,useWrapperDiscovery,useWrappersRegistryAddress,useListPairs,useTokenPair*,useConfidentialTokenAddress,useTokenAddress,useIsConfidentialTokenValid,useUnwrap,useUnwrapAll,useFinalizeUnwrap). - User mentions FHEVM, Zama, TFHE, confidential contracts, encrypted balances, homomorphic computation, confidential dApp, ERC-7984, shielding / unshielding tokens, confidential transfers, the Zama Protocol, the wrappers registry, or the relayer SDK.
- Errors mention any FHEVM custom error: ACL (
SenderNotAllowed,ACLNotAllowed,SenderNotAllowedToUseHandle), input verification (InvalidInputHandle,EmptyInputProof,DeserializingInputProofFail), KMS decrypt (InvalidKMSSignatures,KMSInvalidSigner,EmptyDecryptionProof), runtime (DivisionByZero,NotPowerOfTwo,ZamaProtocolUnsupported), or HCU (HCUTransactionLimitExceeded,HCUTransactionDepthLimitExceeded); or WASM / COOP / COEP issues in an FHEVM project.
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 · 140 lines · 3,675 tokens per session scan A f1dc14bf14ad
fhevm-skill AGENTS.md is an instructions file published in the GitHub repository zunmax/fhevm-skill (2 stars, last pushed 2mo ago), licensed MIT. It adds 3,675 tokens to every session, about $0.0184 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
pumpfun-bonkfun-bot CLAUDE.md
Instructions for chainstacklabs/pumpfun-bonkfun-bot, covering agent guide, ground rules, layout, naming inside learning-examples/ and commands.
evmole AGENTS.md
Instructions for cdump/evmole: EVMole extracts structured facts from deployed EVM runtime bytecode.
VaultysClaw CLAUDE.md
Instructions for vaultys/VaultysClaw, covering claude.md, commands, development, demo / simulator and build.
plamen CLAUDE.md
Instructions for PlamenTSV/plamen, covering plamen — security auditor, execution model, reference files and shared.
solana-developer-platform AGENTS.md
Instructions for solana-foundation/solana-developer-platform, covering solana developer platform, repo layout, source of truth, generated files and public vs internal surfaces.
behavioral-prediction-mcp AGENTS.md
Instructions for ChainAware/behavioral-prediction-mcp, covering chainaware subagent index, agent directory, chainaware-wallet-auditor, chainaware-fraud-detector and chainaware-rug-pull-detector.