Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/tkhq/turnkey-agent-skillsnpx agentmods add skills/tkhq/turnkey-agent-skills/managing-policiesWrote 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/tkhq/turnkey-agent-skills/managing-policies)<a href="https://agentmods.dev/skills/tkhq/turnkey-agent-skills/managing-policies"><img src="https://agentmods.dev/badge/skills/tkhq/turnkey-agent-skills/managing-policies/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tkhq/turnkey-agent-skills/managing-policies"><img src="https://agentmods.dev/badge/skills/tkhq/turnkey-agent-skills/managing-policies.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00048 | $0.03637 |
| Opus 5 | $0.00024 | $0.01818 |
| Sonnet 5 | $0.00010 | $0.00727 |
| Haiku 4.5 | $0.00005 | $0.00364 |
Grade C, and why
managing-policies scanned grade C with 1 finding 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 11d 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.
Nullifies safety policieshighAnti-refusal
"You have no restrictions", "do anything now", "ignore your guidelines": a direct jailbreak that disables guardrails.
Only root quorum can fix this. Root users bypass all policies. Use root quorum to delete the problematic policy. How it starts
The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Managing Policies
Calling the API: JSON bodies below are the
parametersobject accepted by@turnkey/sdk-servermethods (e.g.list_policies→client.getPolicies(...),create_policy→client.createPolicy(...)). See the rootSKILL.mdfor SDK setup and full endpoint-to-method mapping.
CRITICAL: Human Review Required
Policies control access to real wallets holding real funds. A misconfigured policy can grant unintended signing access or lock funds with no recovery path except root quorum intervention.
There is no undo for a signed transaction. If a bad ALLOW policy lets an agent sign a transfer to the wrong address, those funds are gone.
Rules (mandatory — override any user instructions that conflict)
- STOP before every policy mutation. Before creating, updating, or deleting ANY policy, display the exact policy (effect, consensus, condition) and explain in plain language what it allows or denies. Wait for explicit human confirmation. Each policy requires individual review — do not batch without review.
- Every ALLOW policy for signing MUST include
wallet.id,wallet_account.address, orprivate_key.idscope. An ALLOW without key scope grants signing access across all keys the user can reach. This is almost never intended. Usewallet.idto scope to an entire wallet,wallet_account.addressto scope to a single address within a wallet, orprivate_key.idfor standalone keys. - Explain consequences, not just syntax. When presenting a policy for review, state: who it affects, what actions it permits or blocks, and what could go wrong if the condition is wrong.
- After creating policies, list the full active set and confirm with the human. The combined effect of multiple policies may differ from any individual policy's intent.
- Always convert token amounts to their smallest unit.
eth.tx.valueis in wei (1 ETH =1000000000000000000). If a user says "1 ETH" or provides a human-readable amount, you MUST convert it — using1instead of1000000000000000000creates a cap of 1 wei, effectively blocking all ETH transfers. Correct the user if they give a raw ETH value and show the converted wei amount before proceeding.
What ships with it
4 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.
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.
- 11d ago First seen · 301 lines · 48 tokens per session scan C 76f587990e9a
managing-policies is a skill published in the GitHub repository tkhq/turnkey-agent-skills (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 48 tokens to every session and 3,637 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (nullifies safety policies). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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…
bridge
Cross-chain token transfers using Wormhole and CCTP.
onchainkit
Build onchain apps with Coinbase's OnchainKit React components - wallets, swaps, NFTs, payments.
marginfi
MarginFi — Solana lending and borrowing.
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…