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/yeaight7/agent-powerupsWrote 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/yeaight7/agent-powerups/memory-optimize)<a href="https://agentmods.dev/commands/yeaight7/agent-powerups/memory-optimize"><img src="https://agentmods.dev/badge/commands/yeaight7/agent-powerups/memory-optimize/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/yeaight7/agent-powerups/memory-optimize"><img src="https://agentmods.dev/badge/commands/yeaight7/agent-powerups/memory-optimize.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 | $0.00026 | $0.00592 |
| Opus 5 | $0.00013 | $0.00296 |
| Sonnet 5 | $0.00005 | $0.00118 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
memory-optimize 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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Objective
Recommend the cheapest memory workflow that preserves answer quality and future reuse.
Context
Inputs:
- optional path or URL
- optional question or task goal
Optimization targets:
- lower token cost now
- lower reread cost later
- better persistence when repeated queries are likely
Process
- Inspect input shape and reuse horizon:
- plain text or small local file
- noisy web page
- PDF/Office doc or other hard-to-read binary-ish source
- mixed corpus
- existing graph with new question
- existing graph with changed sources
- Check requirements:
apx check graphifyapx check markitdown-file-intakeapx check defuddle
- Recommend exactly one primary path:
- direct read for small, simple, one-shot text
defuddle-> Markdown -> read or build when web chrome is the main problemmarkitdown-file-intake-> Markdown -> read or build when document format is the main problemgraphifyfull build when repeated questions or relationship navigation justify persistent memorygraphify --updatewhen a graph already exists and sources changed- graph query against existing graph when the graph exists and the task is retrieval, tracing, or explanation
- State why that path is cheapest:
- lower immediate token cost
- lower repeated reread cost
- better persistence across future sessions
- Include exact next command(s) for the recommended path.
- If a required tool for the best path is missing, either:
- recommend the next-best lower-capability path that still preserves answer quality, or
- stop and say the missing requirement makes the cheap path unavailable
Stop Conditions
- input is too ambiguous to choose between direct read, helper conversion, build, update, or query
- the recommended path depends on a missing tool and no credible fallback preserves answer quality
- user asks for persistent graph advice but the target path or URL is unavailable
Rules
- optimization target = lower token cost, lower reread cost, better persistence
graphifyis long-lived memory path- helpers are normalization tools only
- keep
graphifyprimary for persistent memory, helpers secondary, Obsidian optional - do not recommend a graph build for trivial one-shot text when direct read is cheaper
- do not claim a helper or graph path is available before requirement checks pass
- do not claim bundled upstream code
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.
- yesterday First seen · 71 lines · 26 tokens per session scan A 3251a2bfa89a
memory-optimize is a command published in the GitHub repository yeaight7/agent-powerups (6 stars, last pushed 2d ago), licensed Apache-2.0. It adds 26 tokens to every session and 592 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 2026-09-14.
Other commands, from other repositories
compound
Document a solved problem to compound team knowledge.
sessions
Manage Claude Code session history, aliases, and session metadata.
save-session
Save current session state to a dated file in /.claude/session-data/ so work can be resumed in a future session with full context.
instinct-import
Import instincts from file or URL into project/global scope.
instinct-status
Show learned instincts (project + global) with confidence.
instinct-export
Export instincts from project/global scope to a file.