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.
npx agentmods add commands/cukas/remembrall/statisticsgit clone --depth 1 https://github.com/cukas/remembrallWhat 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 | $0.00014 | $0.00151 |
| Opus 5 | $0.00007 | $0.00076 |
| Sonnet 5 | $0.00003 | $0.00030 |
| Haiku 4.5 | $0.00001 | $0.00015 |
Grade A, and why
statistics scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Project Statistics
Run the statistics script to display aggregated project intelligence:
bash "$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).
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.
- 2d ago First seen · 21 lines · 14 tokens per session scan A 3b028c2f558b
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.
Other commands, from other repositories
create
Create a complete handover.md so any LLM can continue this session without mistakes.
resume
Load handover.md and brief yourself before continuing a session.
handoff-resume
Resume from a prior session's handoff in .handoffs/.
handoff
Write a session handoff to .handoffs/ before context runs out.
design-review
Workflow recipe — review a design end-to-end, ending in measured numbers rather than adjectives, by chaining 4 skills.
setup-pm-skills
Onboard a new user — find out what they do, recommend the right bundles & top skills, and set up a project CONTEXT.md so every skill is tailored to them.