speckit-companion: Command for Claude Code

.claude/commands/bench-run-all.md

bench-run-all is a command for Claude Code from alfredoperez/speckit-companion. It costs 16 tokens per session (1,046 once invoked), scanned A, original, MIT.

An automated benchmark run for one difficulty level across two versions of a project: standard SpecKit and SpecKit Companion. It prepares both folders, drives their workflows with agents, and records the results for comparison.

In plain words
What is it for?
Use it with an easy, medium, or hard benchmark to run both variants, invoke their agents, and capture comparable results.
Why use it?
It replaces the repeated manual preparation and capture steps and keeps the comparison between the two variants consistent. The results measure relative performance, not a person's exact time using the graphical interface.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

This is alfredoperez/speckit-companion's own configuration. It tells Claude Code how to work on speckit-companion itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything speckit-companion configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is Bash(node ../speckit-bench/run-all.mjs:*), Bash(node ../speckit-bench/sync-templates.mjs:*), Bash(date:*), Bash(git -C:*), Agent, Workflow, AskUserQuestion.

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/alfredoperez/speckit-companion/main/.claude/commands/bench-run-all.md
Clone the repo
git clone --depth 1 https://github.com/alfredoperez/speckit-companion

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.

agentmods badge for bench-run-all

README.md
[![agentmods](https://agentmods.dev/badge/commands/alfredoperez/speckit-companion/bench-run-all/github.svg)](https://agentmods.dev/commands/alfredoperez/speckit-companion/bench-run-all)
Your own site
<a href="https://agentmods.dev/commands/alfredoperez/speckit-companion/bench-run-all"><img src="https://agentmods.dev/badge/commands/alfredoperez/speckit-companion/bench-run-all/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.

agentmods 80×15 button for bench-run-all

Your own site · 80×15
<a href="https://agentmods.dev/commands/alfredoperez/speckit-companion/bench-run-all"><img src="https://agentmods.dev/badge/commands/alfredoperez/speckit-companion/bench-run-all.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,046 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00016 $0.01046
Opus 5 $0.00008 $0.00523
Sonnet 5 $0.00003 $0.00209
Haiku 4.5 $0.00002 $0.00105

Measured 3d ago against content hash 1a0084ba0294, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

bench-run-all 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 3d 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/bench-run-all.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Your task

The automated version of /bench-prep → run it → /bench-capture, for one size. Driver agents work the cells instead of a person.

Size from $ARGUMENTS (easy/medium/hard/oversized).

Faithful dispatch: a driver mimics the GUI, it does not follow raw command bodies. The bench is a trustworthy relative comparator with capture overhead isolated; it does not reproduce a human's absolute wall clock.

1. Check the cells

node ../speckit-bench/run-all.mjs --dry-run — if any cell is missing, run /bench-sync. Note the three versions it prints; they belong in the final report.

2. Prep

node ../speckit-bench/run-all.mjs prep --sizes <size> — resets the cells and writes their run markers into the harness.

3. Drive the three cells (Workflow, parallel)

One driver per cell (parallel of 3). Each works only in ~/dev/projects/conduit-<size>-<letter>, stamps startedAt/finishedAt into ../speckit-bench/runs-meta/conduit-<size>-<letter>.json (via date -u), and runs specify → plan → tasks → implement the GUI-faithful way (see ../speckit-bench/driver.mjs):

  • For EACH step, prepend the same GUI preamble every arm gets — buildStepPreamble(step, specDir) from driver.mjs, which imports the real renderer from dist/ai-providers/promptPreamble.js so it cannot drift — then dispatch the step's command.
    • stock arm → stock /speckit.* command bodies. No capture script; stock is blind by design.
    • Companion arms/speckit.companion.* command bodies, and nothing on top of them. The bodies carry every capture call a run needs. A driver that also runs cap.mjs <step> start writes the start stamp twice — the second is a documented no-op that still costs a round-trip on every step, and it inflated wave A's call count by four. The count that matters comes from the writer's own .trace.jsonl, so the driver has no bookkeeping of its own to do.
  • After dispatching a step, wait for it to settlewaitForSettle(cellDir, step) polls .spec-context.json until the step's completed status or any later one appears. It returns folded: true when the status overshot, which happens for two shipped reasons: the fast path folds specify/plan/tasks onto ready-to-implement, and mark-complete takes implement to completed. A folded step is already done — never re-dispatch it, and never steer the size verdict to make steps settle one at a time. Right-sizing is the feature under measurement; a driver that disables it produces numbers that look valid and are not.
  • Do not time the capture calls. The harness counts them from .trace.jsonl and the timing itself is under the noise floor.

Read the full file on GitHub · 49 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. 3d ago Changed · +15 lines · -5 tokens per session 1a0084ba0294
  2. 11d ago First seen · 34 lines · 21 tokens per session scan A a4567fe8e677

Subscribe to this mod's changes

bench-run-all is a command published in the GitHub repository alfredoperez/speckit-companion (90 stars, last pushed today), licensed MIT. It adds 16 tokens to every session and 1,046 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.

Related

Other commands, from other repositories