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/originprotocol/origin-dollar/actionsnpx skills add OriginProtocol/origin-dollar --skill actionsgit clone --depth 1 https://github.com/OriginProtocol/origin-dollarWrote 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/originprotocol/origin-dollar/actions)<a href="https://agentmods.dev/skills/originprotocol/origin-dollar/actions"><img src="https://agentmods.dev/badge/skills/originprotocol/origin-dollar/actions.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 | $0.00070 | $0.00791 |
| Opus 5 | $0.00035 | $0.00396 |
| Sonnet 5 | $0.00014 | $0.00158 |
| Haiku 4.5 | $0.00007 | $0.00079 |
Grade A, and why
talos-action-development 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 today.
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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Talos Action Development and Maintenance
Runtime Model
- Author actions in
tasks/actions/<actionName>.tswith theaction({...})wrapper fromtasks/lib/action.ts. - Actions self-register and run through
tasks/run.ts; do not import Hardhat or register Hardhat tasks. - Run an action locally with
pnpm exec tsx tasks/run.ts <actionName> --network <network>. Treat a transaction-writing invocation as production-affecting. - Production schedules are defined in
migrations/seed_schedules.sql; the Talos runner loads the generated catalogue fromactions-catalog.json.
Implement an Action
- Match the filename and
namewith camelCase, and provide a clear description and explicitchainsguardrail. - Define every CLI parameter with the
paramsbuilder and keep names camelCase. The generated catalogue converts names to kebab-case flags. - Use the context's
signer,chainId,networkName,log, andargs. Initialise no independent provider or signer unless the action genuinely requires it. - Prefer
getContract("DeploymentName")fromtasks/lib/contractsfor a direct committed deployment binding. For a proxy or interface call, usegetContractAt()with a curated interface ABI or instantiateethers.Contractwith a narrow inline ABI. - Treat committed deployment artifacts,
utils/addresses.js, and action-local chain maps as address sources.artifacts/and Foundrybuild/deployments-<chainId>.jsonare not Talos runtime inputs. - Use named ethers contract methods and
logTxDetailsfor write transactions. Avoid raw selector encoding andsigner.sendTransaction({ to, data })when the method is known. - Validate chain-specific addresses, deployment availability, and signer authority before a transaction. For Safe proposals, preserve simulation, nonce, and delegate checks.
Maintain Existing Actions
- Keep proxy ABI selection deliberate: a deployment artifact supplies an
address, but its ABI may not expose an implementation method. Prefer curated
abi/*.jsoninterfaces for stable proxy calls. - When a Foundry deployment changes an action target, update the corresponding Hardhat deployment address or pinned action address in the same change.
- Preserve idempotency and useful action-specific logging. Do not turn a manual-only or proposal action into an enabled schedule without explicit authorization.
- Avoid co-scheduling two transaction-writing actions for the same signer in a
five-minute window; check
migrations/seed_schedules.sql.
What ships with it
38 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.
- autoValidatorDeposits.ts 722 B runs code
- autoValidatorWithdrawals.ts 836 B runs code
- claimBribes.ts 2.6 KB runs code
- crossChainBalanceUpdateBase.ts 1.3 KB runs code
- crossChainBalanceUpdateHyperevm.ts 1.3 KB runs code
- crossChainRelay.ts 2.4 KB runs code
- crossChainRelayHyperEVM.ts 2.4 KB runs code
- executeGovernorSixProposal.ts 1.2 KB runs code
- harvest.ts 361 B runs code
- healthcheck.ts 721 B runs code
- manageBribeOnSonic.ts 1.1 KB runs code
- manageBribes.ts 1.1 KB runs code
- manageMerklBribes.ts 847 B runs code
- managePassThrough.ts 297 B runs code
- ognClaimAndForwardRewards.ts 926 B runs code
- otokenAddWithdrawalQueueLiquidity.ts 1.6 KB runs code
- otokenOethbHarvest.ts 1.2 KB runs code
- otokenOethbRebase.ts 665 B runs code
- otokenOethbUpdateWoethPrice.ts 625 B runs code
- otokenOethRebase.ts 846 B runs code
- otokenOsCollectAndRelease.ts 1.5 KB runs code
- otokenOsRebase.ts 1.7 KB runs code
- otokenOsSonicRestakeRewards.ts 893 B runs code
- otokenOusdAutoWithdrawal.ts 712 B runs code
- otokenOusdRebase.ts 924 B runs code
- ousdRebalancer.ts 5.1 KB runs code
- permissionedRebase.ts 1.5 KB runs code
- proposeVaultStrategyMoves.ts 8.6 KB runs code
- queueGovernorSixProposal.ts 1.2 KB runs code
- relayCCTPMessage.ts 2.9 KB runs code
- snapBalances.ts 334 B runs code
- sonicClaimWithdrawals.ts 315 B runs code
- stakeValidator.ts 1.0 KB runs code
- undelegateValidator.ts 792 B runs code
- updateVotemarketEpochs.ts 568 B runs code
- verifyBalances.ts 1.4 KB runs code
- verifyDeposits.ts 514 B runs code
- withdrawValidator.ts 774 B runs code
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.
- today First seen · 81 lines · 70 tokens per session scan A 8e5d9cc5d252
talos-action-development is a skill published in the GitHub repository OriginProtocol/origin-dollar (151 stars, last pushed yesterday), licensed MIT. It adds 70 tokens to every session and 791 once invoked, about $0.0003 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 2026-09-04.
Other skills, from other repositories
analyzing-ethereum-smart-contract-vulnerabilities
Perform static and symbolic analysis of Solidity smart contracts using Slither and Mythril to detect reentrancy, integer overflow, access control, and other vulnerability classes before deployment to Ethereum mainnet.
analyzing-ethereum-smart-contract-vulnerabilities
Perform static and symbolic analysis of Solidity smart contracts using Slither and Mythril to detect reentrancy, integer overflow, access control, and other vulnerability classes before deployment to Ethereum mainnet.
web3-bug-classes
Complete reference for all 10 DeFi smart contract bug classes. Use this when hunting for specific vulnerability types, need attack patterns for accounting desync, access control, incomplete path, off-by-one, oracle manipulation, ERC4626 vaults, reentrancy, flash loans, signature replay, or proxy/upgrade bugs.
web3-methodology-research
External research synthesis from Trail of Bits, SlowMist, ConsenSys, Immunefi, and Cyfrin. Use this for advanced audit methodology, Echidna/Medusa fuzzing setup, Slither custom detector writing, attack pattern deep dives, or the 4-phase learning roadmap.
web3-poc-foundry
Complete Foundry PoC writing guide + all cheatcodes + DeFiHackLabs reproduction patterns. Use this when building a proof of concept exploit, setting up a fork test, using Foundry cheatcodes, or reproducing a known DeFi hack for learning.
web3-triage-report
Bug triage validation system, Immunefi report format, and 20 real paid bounty examples dissected. Use this when validating a finding before submitting, writing an Immunefi report, checking if a bug is actually valid, or studying real examples of paid vulnerabilities.