impact

A command that maps which files depend on a file before you edit or refactor it. It follows documented callers up to three levels deep and prints the chain.

In plain words
What is it for?
Use it to inspect a file’s direct and indirect users, review documented constraints, and estimate the files needing attention before an edit.
Why use it?
It helps reveal files that may be affected by a change, including indirect callers that are easy to miss.

Command

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 commands/larens94/codedna/impact
Clone the repo
git clone --depth 1 https://github.com/Larens94/codedna
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 368 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 $0.00018 $0.00368
Opus 5 $0.00009 $0.00184
Sonnet 5 $0.00004 $0.00074
Haiku 4.5 $0.00002 $0.00037

Measured 2d ago against content hash 8793c2c2fa58, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

impact 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 2d 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.

codedna-plugin/commands/impact.md · 48 lines

What it actually says

/codedna:impact $ARGUMENTS

Perform a cascade impact analysis for the file at path $ARGUMENTS.

If no argument is provided, ask: "Which file do you want to analyze? Provide the path relative to the project root."

Steps:

  1. Read the target file's module docstring (first 15 lines only). Extract its exports: and used_by: fields.

  2. For each file listed in used_by:, read only its module docstring and extract its own used_by: (to find second-level callers).

  3. Build the cascade chain — stop at 3 levels deep to avoid infinite loops.

  4. Output the impact tree:

Impact Analysis: utils/format.py
=================================
Direct callers (Level 1):
  - api/routes.py
      exports: revenue_route(req) -> Response
      rules:   all routes require auth middleware
  - views/dashboard.py
      exports: render(ctx) -> str
      rules:   none

Second-level callers (Level 2):
  - workers/report.py  (calls api/routes.py)
      exports: generate(period) -> None

Cascade summary:
  Editing utils/format.py may affect 3 files.
  Check rules: in api/routes.py before changing format_currency signature.
  1. If the file has no used_by: entries or is not annotated, output:
utils/new_file.py has no used_by: entries — no cascade impact detected.
Note: file may not be annotated yet. Run /codedna:check to verify.

Use this command before any refactor, signature change, or deletion.

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. 2d ago First seen · 48 lines · 18 tokens per session scan A 8793c2c2fa58

Subscribe to this mod's changes

impact is a command published in the GitHub repository Larens94/codedna (145 stars, last pushed 6d ago), licensed MIT. It adds 18 tokens to every session and 368 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 2026-08-30.