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.svg" alt="Measured on agentmods" 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 | $0.00015 | $0.00160 |
| Sonnet 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 8d 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.
- 8d ago First seen · 31 lines · 30 tokens per session scan A 5fd413a553ed
memorix-reasoning is a skill published in the GitHub repository AVIDS2/memorix (738 stars, last pushed today), licensed Apache-2.0. It adds 30 tokens to every session and 320 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.
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.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.