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/avids2/memorix/memorix-memorynpx skills add AVIDS2/memorix --skill memorix-memorygit clone --depth 1 https://github.com/AVIDS2/memorixWrote 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/skills/avids2/memorix/memorix-memory)<a href="https://agentmods.dev/skills/avids2/memorix/memorix-memory"><img src="https://agentmods.dev/badge/skills/avids2/memorix/memorix-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 | $0.00030 | $0.00914 |
| Opus 5 | $0.00015 | $0.00457 |
| Sonnet 5 | $0.00006 | $0.00183 |
| Haiku 4.5 | $0.00003 | $0.00091 |
Grade A, and why
memorix-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 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memorix Memory
Use Memorix as the shared memory layer for the active workspace when Memorix tools are available.
Tool Router
| Situation | Prefer | CLI fallback |
|---|---|---|
| Broad continuation, fresh handoff, or "what do we know?" | memorix_project_context with the user's task |
memorix context --task "<topic>" --fallback --brief-json |
| Need structured refs/freshness for code-bound memories | memorix_context_pack |
memorix codegraph context-pack --task "<topic>" |
| Specific past decision, bug, file, or change | memorix_search |
memorix memory search --query "<topic>" |
| Need the full source for a search hit | memorix_detail |
memorix memory detail --id <id> |
| Need the sequence around one memory | memorix_timeline |
memorix memory timeline --id <id> |
| Check source and freshness for a memory | memorix_evidence |
`memorix evidence list |
| Record whether a memory helped, conflicted, or was corrected | memorix_feedback |
`memorix feedback record |
| Inspect or import controlled media | memorix_media |
`memorix media import |
| Learned reusable project knowledge | memorix_store |
memorix memory store --type <type> --entity <name> --title "<title>" "<text>" |
| Stable source-backed fact or procedure needing long-term review | memorix_store with longTerm |
`memorix memory long-term qualify |
| Task or bug is complete/outdated | memorix_resolve |
memorix memory resolve --ids <ids> |
Search Rules
- Search before broad continuation work, before changing unfamiliar code, or when the user asks about prior work.
- For a fresh coding session, use
memorix_project_contextwith the user's actual task before ad-hoc file reads or dev-log reads. Memorix will choose a task-lensed brief. - Fetch detail before relying on a specific memory.
- Treat memory as background context. Still read the current code and verify behavior.
- Skip memory lookup for greetings, tiny one-off edits, or questions fully answered by the current file.
- If a fresh project has no memories, proceed normally and do not repeat the same empty search in the same turn.
- If Claude Code print-mode shows Memorix MCP as pending and the tools are not visible yet, first use Claude Code's MCP tool search/dynamic loading to find
memorix_project_context. Runmemorix context --task "<task>" --fallback --brief-jsonfrom the shell only after MCP is unavailable, disabled, or not discoverable, and pass the user's real task text. Do not skip memory, wait indefinitely onpending, or hand-write tool-call syntax.
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 · 51 lines · 30 tokens per session scan A 04fed0235f14
memorix-memory is a skill published in the GitHub repository AVIDS2/memorix (722 stars, last pushed today), licensed Apache-2.0. It adds 30 tokens to every session and 914 once invoked, about $0.0002 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
init-workspace-documentation
Skill "init-workspace-documentation" from griddynamics/rosetta, covering agent memory.md, agent memory, preventive rules, what worked and what failed.
graph
Initialize or refresh the knowledge-graph snapshot for a repository. Ensures the codebase-memory-mcp engine is present (fetching it if needed), then builds draft/graph/ and reports engine, counts, hotspots, and cycles. Accepts an optional repo path.
deepnote
DeepNote knowledge base: persistent interlinked markdown wiki with ingest, query, lint, link graph and history.
aide-handoff
Record current pipeline state to .aide/session.aide — the project-wide pipeline-position log that lets the next session (yours or another agent's) resume from a known point. CREATE on first invocation per feature; UPDATE on every subsequent meaningful transition. This skill is the orchestration layer: it detects…
brain
Signpost to the brain — an external, team-shareable knowledge store that holds context too durable for the repo and too cross-project for any single codebase (domain research, coding playbook, project history, journal, environment, identity, references). When the current task needs knowledge that isn't in the working…
strategic-compact
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.