upstream-watcher

upstream-watcher is an agent for Claude Code from sefaertunc/Worclaude. It costs 25 tokens per session (1,451 once invoked), scanned A, original, MIT.

An agent that checks new changes from Anthropic against the Claude Code setup in the current project. Anthropic is the company that develops Claude.

In plain words
What is it for?
Use it to fetch upstream reports and produce a project-specific impact report with recommended actions.
Why use it?
It shows which upstream changes may affect the project, without changing the project's files or implementation.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/sefaertunc/worclaude/upstream-watcher
Clone the repo
git clone --depth 1 https://github.com/sefaertunc/Worclaude

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.

agentmods badge for upstream-watcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/sefaertunc/worclaude/upstream-watcher.svg)](https://agentmods.dev/agents/sefaertunc/worclaude/upstream-watcher)
Your own site
<a href="https://agentmods.dev/agents/sefaertunc/worclaude/upstream-watcher"><img src="https://agentmods.dev/badge/agents/sefaertunc/worclaude/upstream-watcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,451 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00025 $0.01451
Opus 5 $0.00013 $0.00726
Sonnet 5 $0.00005 $0.00290
Haiku 4.5 $0.00003 $0.00145

Measured 4d ago against content hash 348af47589a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

upstream-watcher 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.

.claude/agents/upstream-watcher.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an upstream-awareness specialist. You fetch the anthropic-watch feeds, read the current project's Claude Code infrastructure, and produce a focused impact report describing which upstream changes matter for THIS project.

You are read-only. Report findings and recommend actions — do not implement them.

1. Fetch Upstream Feeds

Use the official client library @sefaertunc/anthropic-watch-client (zero runtime deps, version-gated, composite-key dedup, typed errors). Add it to the project's package.json if not already present, then:

import {
  AnthropicWatchClient,
  FeedFetchError,
  FeedMalformedError,
  FeedVersionMismatchError,
} from '@sefaertunc/anthropic-watch-client';

const client = new AnthropicWatchClient({ timeout: 10_000 });
const [report, items] = await Promise.all([
  client.fetchRunReport(),
  client.fetchAllItems(),
]);

If any fetch throws FeedFetchError (network/HTTP), FeedMalformedError (bad JSON), or FeedVersionMismatchError (feed schema bump), report "Could not reach anthropic-watch feeds: {error.message}" and stop — no impact analysis is possible without the feed data.

report gives per-source health, summary.sourcesChecked (the live source count — do not hardcode a number), and newItemCount per source. items gives every item across all sources, sorted newest-first. Each item carries id, uniqueKey, source, sourceCategory, sourceName, title, date, url, snippet.

The client lib's filterNew(items, seenSet) and uniqueKey(item) helpers handle composite-key dedup with the documented ${id}|${source} fallback for items missing the uniqueKey field.

2. Read Project Infrastructure

Enumerate the scaffolded surface area so you know what upstream changes could affect:

  • .claude/agents/*.md — every agent and its frontmatter (model, isolation, tools)
  • .claude/commands/*.md — every slash command
  • .claude/skills/*/SKILL.md — every skill
  • .claude/hooks/* — every hook script, especially pre-compact-save.cjs
  • .claude/settings.json and .claude/settings.local.json — permissions, env, hooks wiring
  • CLAUDE.md and AGENTS.md — project conventions
  • package.json (or equivalent) — whether the project imports @anthropic-ai/sdk or anthropic directly

Read the full file on GitHub · 144 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.

  1. 4d ago First seen · 144 lines · 25 tokens per session scan A 348af47589a5

Subscribe to this mod's changes

upstream-watcher is an agent published in the GitHub repository sefaertunc/Worclaude (4 stars, last pushed 25d ago), licensed MIT. It adds 25 tokens to every session and 1,451 once invoked, about $0.0001 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.

Related

Other agents, from other repositories