Borrowing it
Nothing to install: this file belongs to alfredoperez/speckit-companion. 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/alfredoperez/speckit-companion/main/.claude/commands/bench-replay.mdgit clone --depth 1 https://github.com/alfredoperez/speckit-companionWrote 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/alfredoperez/speckit-companion/bench-replay)<a href="https://agentmods.dev/commands/alfredoperez/speckit-companion/bench-replay"><img src="https://agentmods.dev/badge/commands/alfredoperez/speckit-companion/bench-replay/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/alfredoperez/speckit-companion/bench-replay"><img src="https://agentmods.dev/badge/commands/alfredoperez/speckit-companion/bench-replay.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 | $0.00016 | $0.01549 |
| Opus 5.5 | $0.00006 | $0.00620 |
| Sonnet 5.5 | $0.00003 | $0.00310 |
| Haiku 4.5 | $0.00002 | $0.00155 |
Grade A, and why
bench-replay 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 19d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your task
Answer a single-step question without running a round. The user names a change ("fan-out off", "the new check node", "gentle-ai's classifier") and which step it affects; you replay that step from a staged state, as many ways as the question needs, and grade each. Everything else is held byte-identical, so a difference in the result is the change and nothing else.
This is for "does X help", never for "is the pipeline good today". A round answers the second. A replay costs about $8 and ten minutes; a round costs about $35 and forty. The harness README.md (bench/README.md in speckit-sandboxes) under Stages is the reference; this command is the procedure.
Paths
Shell state does not persist between Bash calls, so start each one with this line:
. .claude/sandboxes-env.sh && eval "$(node "$SANDBOXES_REPO"/bench/paths.mjs --sh)"
It sets $SANDBOXES_REPO (the sibling speckit-sandboxes checkout, whose bench/ folder is the harness) and $BENCH_CELLS_DIR (where the cells are baked). When you hand a path to an agent, expand it first: an agent gets the absolute path, never the variable.
1. Name the question and the variants
$ARGUMENTS is the change. Turn it into:
- the step it affects:
implement,tasks,plan, orspecify - the stage to start from: the one before that step (
post-tasksfor implement,post-planfor tasks,post-specifyfor plan, the baseline for specify) - the variants, each with a one-word label: the shipped behaviour is always one of them and is always labelled
asis
Two variants is the normal shape. Three or more only when the question genuinely has that many arms.
2. Pick the cell and check the build
Pick the arm the question is about. Cells are blind on disk; identify one by what is installed rather than by letter:
for d in "$BENCH_CELLS_DIR"/conduit-*/; do n=$(basename "$d"); c=$([ -d "$d/.specify/extensions/companion" ] && echo companion || echo stock); l=$([ -f "$d/living-specs.yml" ] && echo "+living" || echo ""); echo "$n $c$l"; done
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.
- 19d ago Changed · +10 lines ca398a3ac912
- 1mo ago First seen · 82 lines · 16 tokens per session scan A 7fb4134b6fef
bench-replay is a command published in the GitHub repository alfredoperez/speckit-companion (99 stars, last pushed 6d ago), licensed MIT. It adds 16 tokens to every session and 1,549 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 2026-09-10.
Other commands, from other repositories
debug
Debug code issues with systematic problem-solving and troubleshooting steps.
explain
Explain complex concepts in simple terms with examples and analogies.
zooza-setup
One-time Zooza setup — teaches Claude your business vocabulary so it understands your terms in every future session.
svelte:component
Create new Svelte components with best practices, proper structure, and optional TypeScript support.
enforce.playwright-typescript
Enforce repository-wide compliance with playwright-typescript.instructions.md.
peachflow:init
Initialize peachflow v3 for a project. Creates state file and graph structure. Can reconfigure an existing project.