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 agents/sefaertunc/worclaude/upstream-watchergit clone --depth 1 https://github.com/sefaertunc/WorclaudeWrote 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/agents/sefaertunc/worclaude/upstream-watcher)<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>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 | $0.00025 | $0.01451 |
| Opus 5 | $0.00013 | $0.00726 |
| Sonnet 5 | $0.00005 | $0.00290 |
| Haiku 4.5 | $0.00003 | $0.00145 |
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.
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, especiallypre-compact-save.cjs.claude/settings.jsonand.claude/settings.local.json— permissions, env, hooks wiringCLAUDE.mdandAGENTS.md— project conventionspackage.json(or equivalent) — whether the project imports@anthropic-ai/sdkoranthropicdirectly
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 · 144 lines · 25 tokens per session scan A 348af47589a5
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.
Other agents, from other repositories
context
You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.
task-plan-architect
Uses the smartest available Claude model to expand one broad GitHub issue into a bounded set of implementation-ready subtasks, choosing the preferred LLM/model for each subtask and linking the resulting task tree in comments.
ia-architecture-strategist
Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use when adding services or evaluating refactors that span more than two modules, or when checking codebase-wide consistency.
cursor-rescue
Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, needs a deeper root-cause investigation, or should hand a substantial coding task to Cursor.
security-reviewer
인증, 권한, 결제, 데이터 삭제, 외부 입력 처리 변경 전후에 사용한다.
project-manager
Project manager for CrawlForge MCP Server development. Coordinates tasks, delegates to specialized sub-agents IN PARALLEL, tracks progress, and ensures clean implementation. Use PROACTIVELY for any multi-step project coordination.