benchmark

A command for running performance and benchmark checks in an AIDLC project. Benchmarking means measuring how quickly or efficiently software performs.

In plain words
What is it for?
Use it to run the configured benchmark phase for an epic, read its state, and write the required benchmark summary. If that pipeline has no benchmark phase, it reports that instead.
Why use it?
It connects the benchmark phase to the project's configured workflow instead of assuming which agent or instructions to use.

Command for Claude Code

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/aidlc-io/aidlc/benchmark
Clone the repo
git clone --depth 1 https://github.com/aidlc-io/aidlc

Made for: Claude Code.

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 326 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 $0.00021 $0.00326
Opus 5 $0.00010 $0.00163
Sonnet 5 $0.00004 $0.00065
Haiku 4.5 $0.00002 $0.00033

Measured 2d ago against content hash 0a10cc8d2767, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

benchmark 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.

.claude/commands/benchmark.md · 24 lines

What it actually says

/benchmark — Benchmark

You were invoked as /benchmark <epic> with arguments: $ARGUMENTS (the epic id).

Run the benchmark phase for this epic by following the AIDLC dispatch procedure exactly as /aidlc <epic> benchmark would:

  1. Read docs/epics/<epic>/state.jsonpipelineId.
  2. In .aidlc/workspace.yaml, find that pipeline and its benchmark step (name/agent === benchmark). Use that step's agent + skills — never assume; two pipelines can wire benchmark differently.
  3. If the pipeline has no benchmark step, tell the user this epic's pipeline (<pipelineId>) has no benchmark phase, suggest /aidlc <epic> to run the next eligible phase, and stop.
  4. Otherwise load the persona (.claude/agents/<agent>.md) + skill(s) (.claude/skills/<skill>.md), adopt them (unless the active standard is none), then follow the structural contract: read state/inputs, write to docs/epics/<epic>/artifacts/BENCHMARK-SUMMARY.md (or the step's declared artifact), and tell the user to click "Mark step done".
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 · 24 lines · 0 tokens per session scan A 0a10cc8d2767

Subscribe to this mod's changes

benchmark is a command published in the GitHub repository aidlc-io/aidlc (58 stars, last pushed 28d ago), licensed MIT. It adds 21 tokens to every session and 326 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.