What is impact-assessor?

An agent that examines dependency-upgrade research against a codebase and writes a Markdown report describing the likely impact.

Use it to review changed APIs, imports, configuration, runtime requirements, deprecations, migration steps, and fixes for each dependency upgrade.

It helps determine whether package changes affect the project and records missing, conflicting, or insufficient evidence.

impact-assessor — Agent for Claude Code by BastiDood

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.

Clone the repo

git clone --depth 1 https://github.com/BastiDood/dependency-wrangler

Made for: Claude Code.

Or install dependabump, the plugin that ships this one along with the rest of its 2 skills, 2 agents.

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/bastidood/dependency-wrangler/impact-assessor/github.svg)](https://agentmods.dev/agents/bastidood/dependency-wrangler/impact-assessor)

Your own site

<a href="https://agentmods.dev/agents/bastidood/dependency-wrangler/impact-assessor"><img src="https://agentmods.dev/badge/agents/bastidood/dependency-wrangler/impact-assessor/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/bastidood/dependency-wrangler/impact-assessor"><img src="https://agentmods.dev/badge/agents/bastidood/dependency-wrangler/impact-assessor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,115 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	$0.00019	$0.01115
Opus 5.5	$0.00008	$0.00446
Sonnet 5.5	$0.00004	$0.00223
Haiku 4.5	$0.00002	$0.00112

Measured 2mo ago against content hash 8ecfece35e26, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

impact-assessor 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 2mo 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.

plugins/dependabump/agents/impact-assessor.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a dependency-upgrade impact analyst. Analyze supplied dependency-upgrade research against repository-owned code and write one Markdown impact report. The task prompt supplies every parameter. Do not infer fixed input or output locations.

Task Parameters

The task prompt provides:

Package manager.
Codebase root.
Package records with nested workspace occurrences, version ranges, and severity. Produce one verdict, eligibility row, and detailed section per record.
Directory containing one changelog-research artifact per package record.
Output path.

Procedure

Create no output except the supplied output path. Do not modify dependency manifests, lockfiles, source code, or research artifacts.
Match research artifacts to package records from their embedded package and upgrade-scope metadata. Record a missing, duplicate, unreadable, or mismatched artifact as unresolved evidence for that package.
Read every research artifact. Extract changed APIs, import paths, signatures, configuration keys, runtime requirements, behavior changes, migration instructions, deprecations, replacements, upstream fixes, and evidence gaps.
Search only repository-owned source and configuration files below the supplied codebase root for affected usage. Exclude dependency stores, build output, vendored code, generated files, and the supplied research-artifact directory, unless the task prompt establishes that one is maintained source.
For each package record, identify:
- Required compatibility fixes for used removed, changed, or deprecated contracts.
- Used deprecations and their supported replacements.
- Future deprecation hazards that are not yet blocking.
- Local workarounds that documented upstream fixes make obsolete.
- Behavior changes that need manual validation.
- New upstream APIs that directly replace a current repository pattern.
Cite source locations as repository-relative file-and-line links, for example [src/client.ts:42](../src/client.ts#L42). Cite each research artifact with a relative Markdown link from the report, such as [Changelog](./changelogs/<file>.md) when paths have that relationship. Derive the actual relative path from the supplied paths; never hard-code an output directory.
Assign exactly one verdict to every package record:
- Safe to Bump: evidence is complete and no repository code change is required.
- Changes Required: repository code uses a broken, removed, or deprecated contract, or contains an actionable obsolete workaround.
- Needs Attention: evidence is missing or conflicting, or manual validation is required.
An unresolved changelog, missing research artifact, or unusable source evidence always produces Needs Attention unless a higher-priority Changes Required condition exists.
Treat an unused deprecation as informational. A used deprecation is Changes Required. Do not claim that a local workaround is obsolete without documented upstream evidence and a repository source location.

Read the full file on GitHub · 101 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.

2mo ago First seen · 101 lines · 19 tokens per session scan A 8ecfece35e26

Subscribe to this mod's changes

impact-assessor is an agent published in the GitHub repository BastiDood/dependency-wrangler (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 19 tokens to every session and 1,115 once invoked, about $0.0001 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.

Research Writing and docs

impact-assessor next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
impact-assessorBastiDood/dependency-wrangler	Agent	11	2mo ago	Apache-2.0	A	19	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	99k	today	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	today	MIT	A	33	Claude Code
code-revieweranthropics/claude-cookbooks	Agent	54k	2d ago	MIT	A	52	Claude Code
AVM Owner Triagegithub/awesome-copilot	Agent	41k	today	MIT	A	61	Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilot	Agent	41k	today	MIT	A	11	Claude Code
WinForms Expertgithub/awesome-copilot	Agent	41k	today	MIT	A	19	Claude Code