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.
curl -O https://raw.githubusercontent.com/tensorbee/rdocx/main/.claude/commands/regen-fixtures.mdgit clone --depth 1 https://github.com/tensorbee/rdocxWrote 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/commands/tensorbee/rdocx/regen-fixtures)<a href="https://agentmods.dev/commands/tensorbee/rdocx/regen-fixtures"><img src="https://agentmods.dev/badge/commands/tensorbee/rdocx/regen-fixtures/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.
<a href="https://agentmods.dev/commands/tensorbee/rdocx/regen-fixtures"><img src="https://agentmods.dev/badge/commands/tensorbee/rdocx/regen-fixtures.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00030 | $0.00908 |
| Opus 5.5 | $0.00012 | $0.00363 |
| Sonnet 5.5 | $0.00006 | $0.00182 |
| Haiku 4.5 | $0.00003 | $0.00091 |
Grade A, and why
regen-fixtures 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.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/regen-fixtures [--samples] [--presets] [--corpus] [--baselines]
Rebuild the things in this workspace that are produced by a generator rather
than written by hand. With no flag, does --samples only, which is the safe
default.
The four targets have very different consequences. Read the target's section before running it.
--samples, safe
samples/ holds generated output. It is gitignored, and it is not a fixture
source. Nothing asserts against it, so regenerating it cannot break a test.
cargo run --example <the sample generator>
Use it to eyeball a change by opening the result. If a sample file is what convinced you a change is correct, that belief is not yet a test.
--presets, checked in and diffable
tools/gen-presets/ is an offline generator for the preset shape table, and
its output is checked in so a build never needs the generator.
- Run the generator. If it has not shipped yet, name the story that owns it and stop. Do not hand-produce a preset table.
- Read the diff. An unexpected change in the preset table is the same class of event as an unexpected hash-harness delta, since it feeds geometry for every rendered shape.
- If it is empty, say so and stop. That is the expected result unless the generator or its input changed.
- If it is not empty, the change is its own labelled commit stating what moved and why. Never fold it into a feature commit.
--corpus, fetched, not committed
The deck corpus lives outside the published crates and is fetched rather than
committed, which is why /corpus/ is gitignored.
- Fetch it.
- Report the resolved version or manifest hash. A corpus round-trip
failure with no recent parser change usually means the corpus moved, and
.claude/WORKFLOW.mdlists that as an escalation trigger. You cannot tell which happened without knowing which corpus you have. - Never let a corpus refresh and a parser change land in one commit.
--baselines, the one that needs a reason
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 · 91 lines · 30 tokens per session scan A ef5133d8507e
regen-fixtures is a command published in the GitHub repository tensorbee/rdocx (44 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 908 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.
Other commands, from other repositories
session
Complete guide to managing pair programming sessions.
start
Start a new pair programming session with AI assistance.
red-team
Stress-test a plan, strategy, PRD, or launch with a room of hostile expert personas before you commit.
email-delivery-test
../../services/email/email-delivery-test.md.
email-design-test
../../services/email/email-design-test.md.
email-test-suite
../../services/email/email-test-suite.md.