statistics

A report built from Remembrall’s saved session data. It summarizes frequently changed files, repeated workflow patterns, recurring errors, and session averages.

In plain words
What is it for?
Use it to find file hotspots, identify recurring errors, review test-and-fix patterns, and inspect session statistics after enough sessions have been recorded.
Why use it?
Important project patterns can be spread across many coding sessions and easy to miss. The report brings repeated trouble spots and habits together.

Command

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/cukas/remembrall/statistics
Clone the repo
git clone --depth 1 https://github.com/cukas/remembrall
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 151 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 $0.00014 $0.00151
Opus 5 $0.00007 $0.00076
Sonnet 5 $0.00003 $0.00030
Haiku 4.5 $0.00001 $0.00015

Measured 2d ago against content hash 3b028c2f558b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

statistics 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.

commands/statistics.md · 21 lines

What it actually says

Project Statistics

Run the statistics script to display aggregated project intelligence:

bash "$CLAUDE_PLUGIN_ROOT/scripts/remembrall-statistics.sh" "$(pwd)"

Show the output to the user as-is. The script renders:

  • File hotspots (files frequently touched across sessions)
  • Workflow patterns (test-fix cycles, dominant activities)
  • Recurring errors (errors that appear in multiple sessions)
  • Session statistics (averages per session)

Statistics are aggregated automatically from Pensieve session data on session start. If no statistics exist yet, the user needs at least 3 sessions (configurable via statistics_min_sessions).

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 · 21 lines · 14 tokens per session scan A 3b028c2f558b

Subscribe to this mod's changes

statistics is a command published in the GitHub repository cukas/remembrall (6 stars, last pushed 5mo ago), licensed MIT. It adds 14 tokens to every session and 151 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 2026-08-31.