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/trustless-ai/agent-sdk/claude-mdgit clone --depth 1 https://github.com/trustless-ai/agent-sdkWrote 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/trustless-ai/agent-sdk/claude-md)<a href="https://agentmods.dev/instructions/trustless-ai/agent-sdk/claude-md"><img src="https://agentmods.dev/badge/instructions/trustless-ai/agent-sdk/claude-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 | $0.00548 | $0.00548 |
| Opus 5 | $0.00274 | $0.00274 |
| Sonnet 5 | $0.00110 | $0.00110 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
agent-sdk CLAUDE.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 4d 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agent-sdk
Off-chain SDKs (TypeScript, Python) for ERCs defined in trustless-ai/agent-ercs. Every file in this repo — code, docs, commit messages — is written in English.
What this repo is
agent-ercs defines the on-chain side (Solidity interfaces) of the trustless-ai stack. agent-sdk is the off-chain side: client libraries that call those contracts, and — where an ERC's guarantees allow it — independently re-verify a claim off-chain instead of trusting a third party ("recompute-to-verify").
Adding or updating ERC support
Do not hand-write client code for a new or changed ERC directly. Use the skills:
/add-erc— generate TypeScript and Python clients for an ERC that doesn't have SDK support yet. See.claude/skills/add-erc/SKILL.md./update-erc— refresh existing clients afteragent-ercschanges an ERC's interface. See.claude/skills/update-erc/SKILL.md.
Both skills read the interface and README from the agent-ercs submodule, judge whether the ERC's claims are recompute-to-verify, and write client code, tests (run against a local anvil node via testkit/), and a README documenting the verdict.
Repo layout
agent-ercs/ # git submodule (tracks `main` by default)
testkit/ # shared Foundry harness: deploys contracts to a local anvil node for tests
typescript/src/<category>/<ERCXXXX>/ # TS client + README for each ERC
python/src/agent_sdk/<category>/<ercxxxx>/ # Python client + README for each ERC
Directory names mirror agent-ercs's <category>/<ERCXXXX> structure. TypeScript keeps the exact casing; Python lowercases the ERC segment per PEP 8.
Recompute-to-verify
For each ERC, the ERC's own README.md (under both the typescript/ and python/ implementation directories) records whether its claims can be independently recomputed off-chain from public data, and why. This verdict decides whether the client exposes a verify() method and what the tests must cover — see those per-ERC READMEs for the specifics of any given ERC.
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.
- 4d ago First seen · 36 lines · 548 tokens per session scan A cde2ab377ec8
agent-sdk CLAUDE.md is an instructions file published in the GitHub repository trustless-ai/agent-sdk (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 548 tokens to every session, about $0.0027 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.