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/remembrall-helpgit clone --depth 1 https://github.com/cukas/remembrallWrote 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.
[](https://agentmods.dev/commands/cukas/remembrall/remembrall-help)<a href="https://agentmods.dev/commands/cukas/remembrall/remembrall-help"><img src="https://agentmods.dev/badge/commands/cukas/remembrall/remembrall-help.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00017 | $0.01487 |
| Opus 5 | $0.00009 | $0.00744 |
| Sonnet 5 | $0.00003 | $0.00297 |
| Haiku 4.5 | $0.00002 | $0.00149 |
Grade A, and why
remembrall-help 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Remembrall Help
Show the user this reference:
Commands
| Command | Description |
|---|---|
/remembrall-status |
Diagnostic — check context %, bridge, handoffs, Pensieve, Time-Turner |
/remembrall-help |
This help — list all commands, skills, and config |
/setup-remembrall |
One-time setup — status-line bridge and config |
/autonomous |
Toggle autonomous mode on/off |
/phoenix |
Toggle Phoenix mode on/off — recurring context recycling |
/map |
The Marauder's Map — visual session overview |
/lineage |
Session ancestry DAG — see how sessions branch and chain |
/statistics |
Ambient learning — file hotspots, patterns, recurring errors |
/obliviate |
Memory pruning — analyze and archive stale memories |
/budget |
Context budget — code vs conversation vs memory breakdown |
Skills
| Skill | Description |
|---|---|
/handoff |
Save structured handoff with state, files, git patches |
/replay |
Resume from handoff — verify git state, restore patches |
/pensieve |
Browse and search Pensieve session memories |
/timeturner |
Manage Time-Turner parallel agents — status, diff, merge, cancel |
/obliviate |
Guided memory pruning with user confirmation |
Config (~/.remembrall/config.json)
| Setting | Default | Description |
|---|---|---|
git_integration |
false |
Save git patches before handoff |
team_handoffs |
false |
Copy handoffs to project .remembrall/ |
autonomous_mode |
true |
Skip plan mode for overnight/unattended runs |
retention_hours |
72 |
Hours to keep handoffs before cleanup |
max_transcript_kb |
(auto) | Override max transcript size (rarely needed — bridge calibration handles this) |
pensieve |
true |
Track session intelligence (files, commands, errors) |
pensieve_max_sessions |
3 |
Past sessions to inject on resume |
pensieve_inject_budget |
2000 |
Max chars for Pensieve context injection |
time_turner |
false |
Spawn parallel agent at low context (opt-in) |
time_turner_model |
sonnet |
Model for Time-Turner agent |
time_turner_max_budget_usd |
1.00 |
Budget cap for Time-Turner agent |
threshold_timeturner |
30 |
Context % to trigger Time-Turner |
lineage |
true |
Record session ancestry (parent/child chains) |
lineage_max_entries |
50 |
Max sessions to keep in lineage index |
statistics |
true |
Aggregate Pensieve data into project statistics |
statistics_inject |
false |
Inject statistics into session context |
statistics_min_sessions |
3 |
Min sessions before generating statistics |
obliviate |
true |
Analyze memories for staleness |
obliviate_stale_sessions |
5 |
Sessions without update before memory is stale |
budget_enabled |
false |
Track context budget allocation (opt-in) |
budget_code |
50 |
Target % for code (tool use) content |
budget_conversation |
30 |
Target % for conversation content |
budget_memory |
20 |
Target % for memory/system content |
patrol_integration |
true |
Listen for Patrol signal files |
patrol_signal_ttl |
300 |
Signal expiry in seconds |
phoenix_mode |
false |
Recurring context recycling at urgent threshold |
phoenix_max_cycles |
10 |
Max Phoenix cycles per chain (safety cap) |
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.
- 5d ago First seen · 96 lines · 17 tokens per session scan A b9eeed84a27c
remembrall-help is a command published in the GitHub repository cukas/remembrall (6 stars, last pushed 5mo ago), licensed MIT. It adds 17 tokens to every session and 1,487 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
handoff
Write a session handoff to .handoffs/ before context runs out.
remember
Explicitly save something to memory as an experience.
evolution
Show what the system learned and changed recently.
self-improve
Bootstrap and operate a self-improving agent workspace. Scaffolds .learnings/ and memory/ directories, captures errors and learnings during a session, detects recurring patterns, and promotes stable entries to project memory (CLAUDE.md, AGENTS.md, or references/). Also implements the Proactive Agent pillars — WAL…
cm-share
Author ONE shared cross-project fact from a single claim sentence — verified against the live repo(s), shown to the user, written only on their confirmation.
cm-connect
Hook this repo and another to the shared memory layer end to end — survey, operator-confirmed enrollment, an optional shared fact, absorption both ways, and the network payoff.