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 skills/fhenixprotocol/fhenix-toolkit/fhenix-contractsnpx skills add FhenixProtocol/fhenix-toolkit --skill fhenix-contractsgit clone --depth 1 https://github.com/FhenixProtocol/fhenix-toolkitWrote 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/skills/fhenixprotocol/fhenix-toolkit/fhenix-contracts)<a href="https://agentmods.dev/skills/fhenixprotocol/fhenix-toolkit/fhenix-contracts"><img src="https://agentmods.dev/badge/skills/fhenixprotocol/fhenix-toolkit/fhenix-contracts.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 | $0.00090 | $0.01564 |
| Opus 5 | $0.00045 | $0.00782 |
| Sonnet 5 | $0.00018 | $0.00313 |
| Haiku 4.5 | $0.00009 | $0.00156 |
Grade A, and why
fhenix-contracts 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fhenix-contracts — write confidential Solidity for Fhenix CoFHE
You activate when the user is writing or editing Solidity that uses Fhenix's FHE library: files importing @fhenixprotocol/cofhe-contracts/FHE.sol or fhenix-confidential-contracts, files using euint* / ebool / eaddress types, or prompts like "build a confidential X contract."
Hard rules — never violate
Tight summary. Full explanations: references/hard-rules.md.
- No
if/requireonebool→ useFHE.select(cond, a, b). (concepts/branchless-update.md) FHE.allowThis(x)after every stored encrypted write — or the contract can't reusexnext tx. (concepts/allow-cascade.md)- Avoid encrypted
mul/divwhenshrworks — bit-shifts approximate ratios cheaply. (concepts/bit-shift-ratio.md) - No ciphertext allowance — replace ERC-20
approvewith the operator pattern. (concepts/operator-pattern.md) trivialEncryptexposes plaintext in calldata — only safe for non-secret constants.- Confidentiality is not anonymity — FHE hides values, not the transaction graph.
- Order
allow*before emit / return — the off-chain network observes handles in event/return order and expects ACL bits set first. - Uninitialized encrypted state acts as zero —
euint32 x;reads asFHE.asEuint32(0); track presence with a separate plaintext flag. - Both arms of
FHE.selectalways execute — no short-circuit. Foreaddress, useFHE.asEaddress(address(0))as the false-arm sentinel. allowPublic/allowGlobalare irreversible — there is norevokePublic. Treat them as "publish to the world."- Use ERC-1167 clones, not
new, for large FHE contracts —newembeds child creation code; FHE contracts bust the 24KB EIP-170 limit fast. allowTransientvsallow— pick by lifetime — transient grants don't survive the current tx; never use for SDK decrypts. (concepts/allow-transient.md)
The four ACL verbs
| Verb | Grants | Call when |
|---|---|---|
FHE.allowThis(ct) |
The current contract | After every encrypted write that's stored — mandatory. |
FHE.allowSender(ct) |
msg.sender |
The caller will decrypt off-chain (e.g. show their own balance). |
FHE.allow(ct, addr) |
Specific address | Pass the ciphertext to another contract, or grant a known user. |
FHE.allowPublic(ct) |
Everyone | Intentional protocol reveal. Pair with off-chain decryptForTx(...).withoutPermit() + on-chain FHE.verifyDecryptResult(...). |
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/concepts/allow-cascade.md 2.8 KB
- references/concepts/allow-transient.md 2.5 KB
- references/concepts/bit-shift-ratio.md 2.1 KB
- references/concepts/branchless-update.md 2.2 KB
- references/concepts/confidential-token-standards.md 4.2 KB
- references/concepts/encrypted-input.md 3.8 KB
- references/concepts/handle-lifecycle-backfill.md 5.6 KB
- references/concepts/operator-pattern.md 2.9 KB
- references/concepts/randomness-via-entropy.md 2.8 KB
- references/decision-trees.md 3.3 KB
- references/hard-rules.md 5.3 KB
- references/lookup-recipes.md 4.5 KB
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 · 86 lines · 90 tokens per session scan A 9f21578ba939
fhenix-contracts is a skill published in the GitHub repository FhenixProtocol/fhenix-toolkit (12 stars, last pushed 3mo ago), licensed MIT. It adds 90 tokens to every session and 1,564 once invoked, about $0.0005 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 skills, from other repositories
signature-replay
Signature replay attacks — missing nonces, missing chain ID, ecrecover zero address, signature malleability, cross-chain replay.
official-sui-skills
Pointer to the official Mysten Labs skills for building on Sui — language fundamentals, object model, PTBs, SDKs, publishing, upgrades, frontend integration, accessing on-chain data. Maintained upstream at github.com/MystenLabs/skills; pinned to the same ref the audit catalog derives from (see…
nip85-trusted-assertions
The NIP-85 trusted-assertions model in Quartz (nip85TrustedAssertions/) — kind 10040 trust-provider lists, kind 30382 contact cards / user assertions, 30383 event assertions, 30384 addressable assertions, 30385 external-id assertions. Use when building or parsing these events, working with the typed tags (RankTag…
crypto-market-rank
Crypto market rankings and leaderboards. Query trending tokens, top searched tokens, Binance Alpha tokens, tokenized stocks, social hype sentiment ranks, smart money inflow token rankings, top meme token rankings from Pulse launchpad, and top trader PnL leaderboards. Use this skill when users ask about token rankings…
trading-signal
Subscribe and retrieve on-chain Smart Money signals. Monitor trading activities of smart money addresses, including buy/sell signals, trigger price, current price, max gain, and exit rate. Use this skill when users are looking for investment opportunities — smart money signals can serve as valuable references for…
bridge
Cross-chain token transfers using Wormhole and CCTP.