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 skills/grpcer/ownmem/recallnpx skills add grpcer/ownmem --skill recallgit clone --depth 1 https://github.com/grpcer/ownmemWhat 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 | $0.00066 | $0.00733 |
| Opus 5 | $0.00033 | $0.00367 |
| Sonnet 5 | $0.00013 | $0.00147 |
| Haiku 4.5 | $0.00007 | $0.00073 |
Grade A, and why
recall 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- ownmem — 98% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OwnMem recall and daily use
OwnMem is this repository's local, deterministic memory. Recall runs offline — no model calls, no network, no query-time token cost — and every memory is plain Markdown inside the repository.
If the repository has no .ownmem/ directory, OwnMem is not installed here;
use the init skill from this plugin first.
Recall before changing code
Run one recall for the problem, path, or symbol you are about to touch:
npx ownmem recall -- "problem, path, or symbol"
For natural-language symptoms, pass two or three phrasings in one call and let the deterministic fusion rank them:
npx ownmem recall --multi -- "symptom in plain words" "root-cause term" "english symbol"
Open a hit's full topic file before relying on it, then verify against live code: memories record what was true when they were written.
The three feedback streams
Three different questions, three separate local files, three separate denominators. Nothing here is uploaded, and no stream may stand in for another.
1. Retrieval verdict — did recall return the right thing?
npx ownmem recall --feedback correct -- "query that matched"
npx ownmem recall --feedback retrieval_miss --expected memory_name -- "query that should have matched"
retrieval_miss means the right memory is active but fell outside the top-k,
so it must name it. coverage_gap means no right memory exists yet, so it
never takes --expected. wrong, stale and conflict may name one.
2. Outcome receipt — what happened after a memory was used? Record it only when the user or the host actually confirmed it; an agent's own opinion is refused here on purpose. Only the digest of the confirming statement is stored, never its text.
npx ownmem outcome --memory memory_name --outcome applied \
--confirmed-by user --confirmation "yes, that fixed it"
This is the only honest measure of actual application. Until receipts accumulate, a full-text open still means only that a body was read.
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 · 84 lines · 66 tokens per session scan A 2416d74f28c3
recall is a skill published in the GitHub repository grpcer/ownmem (191 stars, last pushed 5d ago), licensed Apache-2.0. It adds 66 tokens to every session and 733 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
memory-curation
When you have read / processed a workspace asset in this session and learned something durable about it, write a memory page so future sessions benefit. Maintain the workspace wiki's hierarchical structure as it grows.
plur-memory
Persistent learning for AI agents. Open engram format. Your agent learns from corrections, remembers across sessions, and transfers knowledge across domains.
evolve-session-review
Automatically triggered by Stop hook. Reviews session for evolution learnings.
ori-memory
Persistent agent memory with learning retrieval. Knowledge graph on markdown files — capture insights, decisions, research, and learnings during work, then retrieve them weeks or months later. Use when knowledge is too valuable to lose but too much to inject into every prompt.
ogham-research
Structured memory capture for Ogham shared memory. Use when the user wants to store findings, remember something, save what was learned, or capture a decision. Triggers on "remember this", "store this", "save this finding", "save what we learned", "capture this decision", "log this", or any request to persist…
memex-retro
Save insights from completed tasks to Zettelkasten memory.