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 skills add AVIDS2/memorix --skill memorix-reasoninggit 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-reasoning)<a href="https://agentmods.dev/skills/avids2/memorix/memorix-reasoning"><img src="https://agentmods.dev/badge/skills/avids2/memorix/memorix-reasoning/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/skills/avids2/memorix/memorix-reasoning"><img src="https://agentmods.dev/badge/skills/avids2/memorix/memorix-reasoning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00030 | $0.00320 |
| Opus 5.5 | $0.00012 | $0.00128 |
| Sonnet 5.5 | $0.00006 | $0.00064 |
| Haiku 4.5 | $0.00003 | $0.00032 |
Grade A, and why
memorix-reasoning 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
Memorix Reasoning
Use reasoning memory for why a decision was made. Use ordinary memory for what happened.
Tool Router
| Situation | Prefer | CLI fallback |
|---|---|---|
| Store why a decision was made | memorix_store_reasoning |
memorix reasoning store --entity <name> --decision "<decision>" --rationale "<why>" |
| Find earlier rationale | memorix_search_reasoning |
memorix reasoning search --query "<topic>" |
| Need a stable evolving topic key | memorix_suggest_topic_key |
memorix memory suggest-topic-key --type decision --title "<title>" |
| Link rationale to commit evidence | relatedCommits on reasoning store |
memorix reasoning store ... --relatedCommits <sha> |
Use Reasoning When
- The answer depends on alternatives considered, constraints, expected outcomes, or accepted risks.
- A future agent may otherwise reopen the same debate.
- The user chose a direction and the reason matters more than the implementation details.
- A Git Memory entry says what changed, but not why it changed.
Do Not Use Reasoning For
- Simple progress notes.
- Mechanical refactors with no decision.
- Facts that belong in
memorix_storeashow-it-works,what-changed, orproblem-solution.
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 · 31 lines · 30 tokens per session scan A 5fd413a553ed
memorix-reasoning is a skill published in the GitHub repository AVIDS2/memorix (858 stars, last pushed today), licensed Apache-2.0. It adds 30 tokens to every session and 320 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 2026-08-30.
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.
superskill
Routes authorized coding work through the superskill project knowledge graph and verified rules. Use when this host exposes superskill MCP tools or a repository is initialized with superskill, for project-scoped context, task routing, rules, review, or lifecycle operations.
deepnote
DeepNote knowledge base: persistent interlinked markdown wiki with ingest, query, lint, link graph and history.
strategic-compact
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.