A workflow for updating TypeScript, Python, Rust, and Go software-development-kit clients after an ERC interface or meaning changes. An ERC is a defined interface or contract used by the agent-ercs project.

Use it to compare a changed ERC with existing clients, update contract wrappers, and add or revise pure recomputation functions and tests when needed.

It helps keep client libraries aligned with changed specifications and identifies when their independently calculated results also need updating.

How trustless-ai/agent-sdk configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to trustless-ai/agent-sdk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/trustless-ai/agent-sdk/main/.claude/skills/update-erc/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/trustless-ai/agent-sdk

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/trustless-ai/agent-sdk/update-erc/github.svg)](https://agentmods.dev/skills/trustless-ai/agent-sdk/update-erc)

Your own site

<a href="https://agentmods.dev/skills/trustless-ai/agent-sdk/update-erc"><img src="https://agentmods.dev/badge/skills/trustless-ai/agent-sdk/update-erc/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/trustless-ai/agent-sdk/update-erc"><img src="https://agentmods.dev/badge/skills/trustless-ai/agent-sdk/update-erc.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,685 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00058	$0.02685
Opus 5.5	$0.00023	$0.01074
Sonnet 5.5	$0.00012	$0.00537
Haiku 4.5	$0.00006	$0.00268

Measured 1mo ago against content hash 74d39a4def04, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

update-erc 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 1mo 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.

.claude/skills/update-erc/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update ERC

Refresh SDK support for an ERC that agent-sdk already implements, after agent-ercs changed something about it. Like add-erc, the output has two layers:

Layer 1 — contract wrappers: client.ts / client.py
Layer 2 — pure recompute: recompute.ts / recompute.py

Process

Determine what changed. If not specified, ask which ERC changed in agent-ercs, and what changed (or point to the commit/PR). Check out the relevant agent-ercs ref if it differs from what's currently checked out.
Diff against what's implemented. Compare the current agent-ercs interface against the existing clients for all four languages. Check whether the recompute layer files exist:
- typescript/src/<category>/<ERCXXXX>/recompute.ts + test
- python/src/agent_sdk/<category>/<ercxxxx>/recompute.py + test
- rust/core/src/<erc_lowercase>/recompute.rs (inline #[cfg(test)])
- go/<category>/<erc_lowercase>/recompute.go + recompute_test.go
If they're missing and the ERC has spec changes (or had recompute-able claims that were never extracted), flag that Layer 2 needs to be created.
Re-classify only if warranted. Re-run the recompute-to-verify classification (see add-erc's step 3) only if the interface or semantics changed in a way that could affect the verdict. Otherwise, carry the existing verdict forward unchanged.
Identify pure recompute functions (Layer 2). For each claim the ERC makes, determine whether it involves a deterministic computation reproducible off-chain as a pure function. This is SEPARATE from recompute-to-verify classification (step 3). See add-erc's step 4 for the full methodology and examples.

Read the conformance vectors at /Users/shakku/code/recompute-kit/conformance/agent-flow.vectors.json — cross-reference the step field with the ERC's claims. Any new or changed pure recompute functions from the spec update should be reflected here.

If the recompute layer files already exist, diff them against any spec changes to the ERC and update accordingly. If they're missing and the ERC has pure recompute claims, plan to generate them.

Read the full file on GitHub · 109 lines

Changes

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.

1mo ago First seen · 109 lines · 58 tokens per session scan A 74d39a4def04

Subscribe to this mod's changes

update-erc is a skill published in the GitHub repository trustless-ai/agent-sdk (2 stars, last pushed 20d ago), licensed Apache-2.0. It adds 58 tokens to every session and 2,685 once invoked, about $0.0002 per session on Opus 5.5. 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.

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

agent-sdk: Skill for Claude Code