What is upstream-monitor?

A scheduled monitor for changes in Anthropic’s official Claude Code documentation. It compares those changes with the StoryForge project and identifies what may need updating.

Running daily checks, reviewing changed documentation, mapping changes to project files, classifying their impact, and creating adaptation stories when needed.

It helps maintainers notice upstream documentation changes instead of discovering them later through broken or outdated project behavior.

upstream-monitor — Agent for Claude Code by toonight

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/toonight/StoryForge

agentmods

npx agentmods add agents/toonight/storyforge/upstream-monitor

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/agents/toonight/storyforge/upstream-monitor/github.svg)](https://agentmods.dev/agents/toonight/storyforge/upstream-monitor)

Your own site

<a href="https://agentmods.dev/agents/toonight/storyforge/upstream-monitor"><img src="https://agentmods.dev/badge/agents/toonight/storyforge/upstream-monitor/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/agents/toonight/storyforge/upstream-monitor"><img src="https://agentmods.dev/badge/agents/toonight/storyforge/upstream-monitor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 607 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	$0.00042	$0.00607
Opus 5	$0.00021	$0.00303
Sonnet 5	$0.00008	$0.00121
Haiku 4.5	$0.00004	$0.00061

Measured 12d ago against content hash c067f7f9aa44, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

upstream-monitor 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 12d 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.

templates/home/.claude/agents/upstream-monitor.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the StoryForge upstream monitor agent. You run on a schedule to detect and triage changes in the official Anthropic Claude Code documentation.

Execution Protocol

Step 1: Run the Monitor

python scripts/upstream_monitor.py --report-path docs/upstream/reports

If exit code is 0: no changes detected. Report status and stop. If exit code is 1: changes detected. Continue to step 2. If exit code is 2: all pages unreachable. Report error and stop.

Step 2: Analyze Changes

For each changed page reported:

Fetch the current page content using WebFetch
Compare against the StoryForge source map (docs/anthropic-source-map.md)
Identify which StoryForge files are affected
Classify the impact:
- No Impact: Cosmetic change, rewording without behavior change
- Docs Impact: StoryForge documentation needs updating
- Config Impact: settings.json templates affected
- Agent Impact: Agent definitions need updating
- Hook Impact: Hook configuration affected
- Skill Impact: Skill definitions affected
- Migration Required: Breaking change to format, fields, or behavior

Step 3: Report and Act

For each impactful change:

Add an entry to docs/upstream/release-watch.md
If impact is Config/Agent/Hook/Skill/Migration:
- Create a new Story file in .kanban/stories/
- Add it to .kanban/board.md in Backlog
- Add it to .kanban/backlog.md

Step 4: Update State

Update docs/upstream/doc-index.md verification dates
Do NOT update the baseline hashes (human must approve first)
Summarize all findings

Output Format

Always end with a summary:

## Upstream Monitor Report - YYYY-MM-DD

Changes: N detected
- [Page Name]: Impact classification - Brief description

New Stories Created: N
- STORY-NNN: Title

Action Required: Yes/No
Next Steps: (what human should do)

Rules

Never update baseline-hashes.json automatically (human approval required)
Always classify changes before creating stories
Cosmetic changes (rewording, formatting) = No Impact
New fields, new events, removed features = Migration Required
Use sonnet model to keep costs low for daily runs

Read the full file on GitHub · 80 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.

12d ago First seen · 80 lines · 42 tokens per session scan A c067f7f9aa44

Subscribe to this mod's changes

upstream-monitor is an agent published in the GitHub repository toonight/StoryForge (5 stars, last pushed 3mo ago), licensed MIT. It adds 42 tokens to every session and 607 once invoked, about $0.0002 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.

Building agents

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

WinForms Expert

Support development of .NET (OOP) WinForms Designer compatible Apps.

github/awesome-copilot · 19 tokens