A read-only impact assessment for a type, function, crate, file, project part, or feature story. It searches for users and classifies whether changing the target affects internal code, public interfaces, or stored data.

Use it to trace references across a Rust workspace, count affected crates, identify public API and serialized-data risks, and assess an F-ID's planned change surface.

It answers what may break before a change is made. This helps distinguish a local edit from a change that needs compatibility decisions or round-trip checks for saved data.

How tensorbee/rdocx configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to tensorbee/rdocx. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/tensorbee/rdocx/main/.claude/commands/impact.md

Clone the repo

git clone --depth 1 https://github.com/tensorbee/rdocx

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/commands/tensorbee/rdocx/impact/github.svg)](https://agentmods.dev/commands/tensorbee/rdocx/impact)

Your own site

<a href="https://agentmods.dev/commands/tensorbee/rdocx/impact"><img src="https://agentmods.dev/badge/commands/tensorbee/rdocx/impact/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/commands/tensorbee/rdocx/impact"><img src="https://agentmods.dev/badge/commands/tensorbee/rdocx/impact.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 755 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	$0.00013	$0.00755
Opus 5.5	$0.00005	$0.00302
Sonnet 5.5	$0.00003	$0.00151
Haiku 4.5	$0.00001	$0.00076

Measured 26d ago against content hash 4c68f54d81cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 26d 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.

.claude/commands/impact.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/impact

Answer "what breaks if I change this?" before the change is made. The target is a type, a function, a crate, a part name or an F-ID.

Read-only. Produces an assessment, not a diff.

Steps

Resolve the target. A symbol, a file, a crate, or an F-ID whose design plan names the surface it touches.
Find the direct users. Search the workspace for every reference. Report the count per crate, because a change confined to one crate is a different proposition from one crossing three.

Classify the surface.

Class	Consequence
Crate-private	Free to change
Workspace-internal	Mechanical, one commit
Published API of a released crate	Semver decision. Name the crate and its version
Leaked type	Worse than it looks, see below
Serialised to disk	Round-trip and corpus consequences

Leaked types are the trap here. rdocx's public API exposes rdocx-oxml and rdocx-layout types (CT_PPr, CT_SectPr, VMerge, Twips, FontFile) without re-exporting them. A change to one of those is a breaking change to rdocx even though nothing in rdocx mentions it.

Check the render path. Does the target feed layout, shaping, colour resolution or PDF emission? If so, the hash harness will move, and that is a fact about the change rather than a risk of it. Say so, and say whether the delta is expected to be explicable.
Check the corpus path. Does it affect parsing or serialisation of a part type? If so the round-trip gate applies, and for pptx the "opens without repair" gate applies too.
Check the spec. Which docs/hld/ sections describe the current behaviour. Those are the ## HLD impact list for whatever story does this.
Report as: blast radius, semver verdict, harness and corpus consequences, the HLD files to update, and a suggested story size.

Worked shape

Target: oxml_layout::PositionedElement

Blast radius
  oxml-pdf         12 sites (writer.rs 8, raster.rs 3, font.rs 1)
  rdocx-layout     31 construction sites
  rpptx-render     future consumer

Surface class
  Published API of oxml-layout. Also reachable through rdocx's public API.

Semver
  Adding a variant is breaking unless the enum is #[non_exhaustive].
  Take that once, at the 0.3.0 cut.

Harness
  No delta expected if existing variants are untouched. Verify, do not assume.

HLD impact
  docs/hld/08-rendering-spec.md, "Extending PositionedElement"

Suggested size
  M, if additive. L if any existing variant changes shape.

Read the full file on GitHub · 83 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.

26d ago First seen · 83 lines · 13 tokens per session scan A 4c68f54d81cd

Subscribe to this mod's changes

impact is a command published in the GitHub repository tensorbee/rdocx (44 stars, last pushed yesterday), licensed MIT. It adds 13 tokens to every session and 755 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 2026-10-04.

Code review Planning

rdocx: Command for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/impact

Steps

Worked shape

What this file has done since we first saw it

Other commands, from other repositories

refactor

review-branch

init

spec-trace-requirements

merge-conflict-analysis

boot