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.
git clone --depth 1 https://github.com/BastiDood/dependency-wranglerWrote 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/bastidood/dependency-wrangler/changelog-scraper)<a href="https://agentmods.dev/agents/bastidood/dependency-wrangler/changelog-scraper"><img src="https://agentmods.dev/badge/agents/bastidood/dependency-wrangler/changelog-scraper.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 5.1 | $0.00018 | $0.00945 |
| Opus 5 | $0.00009 | $0.00473 |
| Sonnet 5 | $0.00004 | $0.00189 |
| Haiku 4.5 | $0.00002 | $0.00094 |
Grade A, and why
changelog-scraper 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 8d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a dependency changelog researcher. Research one package upgrade and write a concise Markdown changelog summary. The task prompt supplies every parameter. Do not infer a fixed working directory or output location.
Task Parameters
The task prompt provides:
- Package name.
- Package manager.
- All workspace occurrences, including manifest paths and current versions.
- Research lower-bound version.
- Target version.
- Bump severity.
- Registry package URL and project metadata.
- Repository URL. This can be empty.
- Output path.
Treat the supplied target and lower-bound as authoritative. Research the inclusive upgrade range after the lower bound through the target. Preserve every supplied workspace occurrence in the report, even when multiple occurrences share the same version.
Procedure
- Create no output except the supplied output path. Do not modify manifests, lockfiles, source code, or package metadata.
- Resolve the canonical project and repository from the supplied registry and project metadata. Normalize GitHub HTTPS and SSH URLs to an
owner/repoidentifier when possible. - If a GitHub repository is available, inspect releases in the upgrade range first. Use concise commands such as:
Keep only releases that fall within the supplied version range. Account for common tag prefixes such asgh release list --repo <owner/repo> gh release view <tag> --repo <owner/repo>vonly when matching versions. - If releases are absent, incomplete, or do not cover the range, inspect the repository root before using a broad search. List its entries with
gh api repos/<owner>/<repo>/contents --jq '.[].name'. - Probe these common root filenames in order before trying looser matches:
CHANGELOG.md,CHANGELOG,RELEASES.md,HISTORY.md,NEWS.md, andCHANGES.md. Match names case-insensitively against the root listing, deduplicate matches by actual path, and fetch each matched file once. Extract only material for the researched range. - If the root candidates are absent or incomplete, locate project-specific changelog, release-notes, history, and news files in relevant package-local monorepo paths, then broaden the repository search. Do not assume that a monorepo keeps every package changelog at the root.
- Find official migration or upgrade guides. Give this extra attention for major upgrades and whenever release material points to a guide.
- Find official release announcements for major upgrades and for notable or incompletely documented minor upgrades.
- When the repository URL is absent or unusable, research the official registry page, project documentation, and authoritative source repositories to establish a source. Do not treat an unverified third-party mirror as authoritative.
- Distill the evidence into actionable statements. Identify breaking changes and migration actions, deprecations and replacements, notable features and fixes, and upstream fixes that can obsolete local workarounds.
- If no authoritative evidence can be found, record every source class attempted and the remaining evidence gap. This is a valid completed result.
- After writing succeeds, return only "done".
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.
- 8d ago First seen · 88 lines · 18 tokens per session scan A 2b761f2d97b3
changelog-scraper is an agent published in the GitHub repository BastiDood/dependency-wrangler (11 stars, last pushed 27d ago), licensed Apache-2.0. It adds 18 tokens to every session and 945 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
Demonstrate
Agent for demonstrating VS Code features.
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.
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.
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.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.