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.
git 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/budget)<a href="https://agentmods.dev/commands/cukas/remembrall/budget"><img src="https://agentmods.dev/badge/commands/cukas/remembrall/budget/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/cukas/remembrall/budget"><img src="https://agentmods.dev/badge/commands/cukas/remembrall/budget.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00013 | $0.00302 |
| Opus 5.5 | $0.00005 | $0.00121 |
| Sonnet 5.5 | $0.00003 | $0.00060 |
| Haiku 4.5 | $0.00001 | $0.00030 |
Grade A, and why
budget scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Context Budget
Check the budget analysis for the current session:
SESSION_ID="${CLAUDE_SESSION_ID:-}"
REPORT="/tmp/remembrall-budget/${SESSION_ID}.json"
If the report exists, display the budget breakdown:
cat "$REPORT" | jq -r '"Code: \(.code_pct)% (budget: \(.budget.code)%)\nConversation: \(.conversation_pct)% (budget: \(.budget.conversation)%)\nMemory: \(.memory_pct)% (budget: \(.budget.memory)%)"'
Show the user:
- Current allocation per category (code, conversation, memory) as percentages
- Configured budget limits
- Any warnings where actual exceeds budget by >10 points
If budget_enabled is false, inform the user:
- Budget tracking is opt-in:
remembrall_config_set "budget_enabled" "true" - Default allocations: code 50%, conversation 30%, memory 20%
- Budgets must sum to 100%
If easter_eggs are enabled and there's an imbalance, use the Sorting Hat theme: "The Sorting Hat detects an imbalance! [House] has claimed N% of the common room."
Where houses map to: code=Ravenclaw, conversation=Gryffindor, memory=Hufflepuff.
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.
- 1mo ago First seen · 35 lines · 13 tokens per session scan A dc59aaaebcc1
budget is a command published in the GitHub repository cukas/remembrall (6 stars, last pushed 6mo ago), licensed MIT. It adds 13 tokens to every session and 302 once invoked, about $0.0001 per session on Opus 5.5. 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.
budget
Manage the token budget for Claude Code sessions. Model-aware — picks the right effective context window and prices per model. The session's REAL model is read from the transcript by the budget hook; config.model is only the fallback. Everything from Sonnet 4.6 up is 1M; Haiku 4.5 is 200K.
orchestrate
Do this task as an orchestrator. The aim is the same result at a fraction of the cost: in a long session, every token in this conversation is re-read on each later request, while a subagent's reading is discarded when it returns. The plugin's subagents run on Haiku 5.5, about 40× cheaper per token than Opus 5.5.
promote
Move .memory/ artifacts to permanent knowledge locations.
checkpoint
Create or update .memory/ with current conversation state.
cleanup
Delete promoted content from the .memory/ directory.