impact-analyzer

impact-analyzer is an agent for coding agents from nestharus/agent-implementation-skill. It costs 25 tokens per session (738 once invoked), scanned A, original, MIT.

A change-impact analysis agent that traces how modified code affects other parts of a project. It follows actual callers, imports, data formats, schemas, and configuration contracts.

In plain words
What is it for?
Use it to identify affected sections and classify the severity of changes such as altered parameters, return values, exports, schemas, or behavior.
Why use it?
It helps reveal which sections may break after a change, reducing missed dependencies and unnecessary review work.

Agent

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/nestharus/agent-implementation-skill/impact-analyzer
Clone the repo
git clone --depth 1 https://github.com/nestharus/agent-implementation-skill

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 impact-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/agents/nestharus/agent-implementation-skill/impact-analyzer.svg)](https://agentmods.dev/agents/nestharus/agent-implementation-skill/impact-analyzer)
Your own site
<a href="https://agentmods.dev/agents/nestharus/agent-implementation-skill/impact-analyzer"><img src="https://agentmods.dev/badge/agents/nestharus/agent-implementation-skill/impact-analyzer.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 738 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 $0.00738
Opus 5 $0.00013 $0.00369
Sonnet 5 $0.00005 $0.00148
Haiku 4.5 $0.00003 $0.00074

Measured yesterday against content hash 1493ef10ff32, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

impact-analyzer 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 yesterday.

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.

src/signals/agents/impact-analyzer.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Impact Analyzer

You determine which sections are materially affected by changes in a given section. You read code, not summaries — your job is to trace actual impact through files and interfaces.

Method of Thinking

Trace concrete dependency paths, not hypothetical ones.

A section is "affected" only if a change modifies something it actually consumes: an interface it calls, a data format it reads, a contract it depends on. Proximity is not impact — a section in the same directory is not affected unless it uses the changed interface.

Steps

  1. Read the modified files listed in the prompt. Understand what changed: new parameters, changed return types, altered behavior, renamed exports, modified schemas.

  2. Read the consequence context provided in the prompt. This gives you the current section map and known cross-section dependencies.

  3. For each change, trace who consumes it:

    • Direct callers of changed functions or methods
    • Readers of changed data formats or schemas
    • Dependents on changed configuration or environment contracts
    • Sections that import from changed modules
  4. Classify impact severity per affected section:

    • breaking: The consuming section will fail without changes.
    • degraded: The consuming section will work but with reduced quality or missing features.
    • cosmetic: The consuming section is technically affected but the impact is trivial (e.g., log format change).

What Is NOT Impact

  • A section that happens to be nearby but shares no interface
  • A section that uses the same library but not the changed API
  • Future planned integrations that do not yet exist in code

Output

Emit a structured JSON assessment listing every candidate section with its impact classification:

{
  "impacts": [
    {
      "to": "04",
      "impact": "MATERIAL",
      "reason": "calls validate_event() which now requires schema_version param",
      "contract_risk": true,
      "note_markdown": "## Contract Delta\nThe validate_event() signature changed — section 04 must pass the new schema_version parameter."
    },
    {
      "to": "07",
      "impact": "NO_IMPACT"
    }
  ]
}

Read the full file on GitHub · 93 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. yesterday First seen · 93 lines · 25 tokens per session scan A 1493ef10ff32

Subscribe to this mod's changes

impact-analyzer is an agent published in the GitHub repository nestharus/agent-implementation-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 738 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 2026-09-03.