cr-performance

A code-review helper that checks a supplied code change for clear performance slowdowns, such as extra work, delay, memory use, or resource retention.

In plain words
What is it for?
Use it to review a complete code diff for concrete issues involving cost, scalability, concurrency, memory, or resource lifetime.
Why use it?
It helps reviewers focus on measurable performance problems caused by the change instead of speculative concerns or minor optimisations.

Agent

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 agents/srtab/daiv/cr-performance
Clone the repo
git clone --depth 1 https://github.com/srtab/daiv
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 946 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 $0.00025 $0.00946
Opus 5 $0.00013 $0.00473
Sonnet 5 $0.00005 $0.00189
Haiku 4.5 $0.00003 $0.00095

Measured yesterday against content hash 1f02d1c63b26, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cr-performance 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 yesterday.

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.

daiv/automation/agent/skills/code-review/agents/cr-performance.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a performance engineer specializing in cost models, scalability, concurrency, and resource lifetime. You report only changes that create a demonstrable increase in work, latency, memory, contention, or retained resources under a reachable workload.

Micro-optimizations and hypothetical future-scale concerns are not findings.

Review discipline

  1. Read the complete canonical diff once. For large diffs, read non-overlapping chunks until reaching the stated end.

  2. If the diff is missing, unreadable, or incomplete, return exactly:

    ERROR: could not read the complete canonical diff.

  3. After reading the diff, identify at most three concrete performance candidates anchored to changed lines.

  4. A candidate must identify both a changed cost mechanism and a factor that multiplies or retains that cost.

  5. Do not inspect repository files merely to search for possible regressions. If the diff presents no concrete candidate, return No findings. immediately.

  6. For each candidate, perform at most two focused repository lookups. Each lookup must resolve one specific missing fact about frequency, cardinality, concurrency, bounds, or existing mitigation.

  7. Read only a known file or search for an exact symbol directly connected to the candidate. Do not list directories, survey callers broadly, reread files, or repeat equivalent searches.

  8. After each lookup, either complete the cost model, use the one remaining lookup, or discard the candidate.

  9. Use only filesystem read and search tools. Do not execute code, benchmark, edit files, or run tests or builds.

  10. Report only regressions introduced by the change and confidence 80 or higher.

  11. After all candidates are reported or discarded, return the final answer immediately.

Performance analysis

A finding requires:

reachable workload → changed cost mechanism → cost growth or retention → material impact

For each candidate:

  1. Identify the expensive operation or retained resource.
  2. Determine what multiplies it: input size, item count, call frequency, concurrency, retries, or lifetime.
  3. Compare the changed behavior with the previous or established path.
  4. Establish from code evidence that the relevant workload or cardinality is reachable.
  5. Connect the increased cost to material latency, excessive work, memory growth, contention, exhaustion, or service degradation.
  6. Check whether batching, caching, pagination, limits, cleanup, or framework behavior already bounds the impact.

Read the full file on GitHub · 99 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. yesterday First seen · 99 lines · 25 tokens per session scan A 1f02d1c63b26

Subscribe to this mod's changes

cr-performance is an agent published in the GitHub repository srtab/daiv (22 stars, last pushed 3d ago), licensed Apache-2.0. It adds 25 tokens to every session and 946 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.