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/sifxprime/kodelyth-ecc/memorygit clone --depth 1 https://github.com/sifxprime/kodelyth-eccWrote 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/sifxprime/kodelyth-ecc/memory)<a href="https://agentmods.dev/commands/sifxprime/kodelyth-ecc/memory"><img src="https://agentmods.dev/badge/commands/sifxprime/kodelyth-ecc/memory.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 | $0.00021 | $0.00453 |
| Opus 5 | $0.00010 | $0.00227 |
| Sonnet 5 | $0.00004 | $0.00091 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade A, and why
memory 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.
What it actually says
/memory
Local self-learning memory. Everything stays on this machine.
Subcommands
/memory
Show storage stats and the 5 most recent memories for this project.
/memory recall <query>
Search memory for <query> using BM25 keyword + tag retrieval. Surfaces the top 5 relevant matches.
Example:
/memory recall stripe webhook signature
/memory remember "<title>"
Capture a new memory. The agent will:
- Ask for the approach (what worked) and any gotchas
- Auto-extract tags and language from the conversation
- Show you the proposed memory
- Store only after you confirm
/memory review-pending
Show the queue of candidate memories extracted automatically by the Stop hook from your last session. Confirm each one to store, or skip.
/memory forget <id>
Mark a memory deleted. It's a soft-delete (the row stays in the log marked deleted: true) so you can recover it by editing ~/.kodelythecc/memory/memories.jsonl.
/memory list
Show all stored memories — id, date, language, problem, tags.
/memory rebuild
Rebuild the BM25 index from memories.jsonl. Run this if search results look stale or if you've manually edited the log.
/memory inject [--query <text>]
Print the cache-friendly context block that the SessionStart hook would inject. Useful for debugging what your AI sees about you.
Implementation
This command delegates to:
node ~/.claude/scripts/memory/cli.js <subcommand> [args]
Or invoke the agent directly:
use kodelyth-memory
Storage location
~/.kodelythecc/memory/ (override with KODELYTH_MEMORY_DIR env var)
memories.jsonl— the source of truthindex.json— BM25 inverted indexpending-review.jsonl— Stop-hook candidates awaiting confirmation
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 · 63 lines · 21 tokens per session scan A b25d26817133
memory is a command published in the GitHub repository sifxprime/kodelyth-ecc (11 stars, last pushed 3d ago), licensed MIT. It adds 21 tokens to every session and 453 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 2026-09-03.
Other commands, from other repositories
csm-governance
Run memory governance — dedup detection, candidate and archive reports, merges.
csm-recall
Search project memory and assemble focused evidence for the current task.
csm-beliefs
Review belief knowledge, run a belief scan, and preview promotions.
csm-brief
Build a context brief for the current task from prior sessions.
csm-checkpoint
Create or inspect durable checkpoints of expensive-to-reconstruct state.
csm-compaction
Show context pressure and audit compaction behavior.