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 MathClaw-ruc/MathClaw --skill memorygit clone --depth 1 https://github.com/MathClaw-ruc/MathClawWrote 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/mathclaw-ruc/mathclaw/memory)<a href="https://agentmods.dev/skills/mathclaw-ruc/mathclaw/memory"><img src="https://agentmods.dev/badge/skills/mathclaw-ruc/mathclaw/memory/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/mathclaw-ruc/mathclaw/memory"><img src="https://agentmods.dev/badge/skills/mathclaw-ruc/mathclaw/memory.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00013 | $0.00551 |
| Opus 5.5 | $0.00005 | $0.00220 |
| Sonnet 5.5 | $0.00003 | $0.00110 |
| Haiku 4.5 | $0.00001 | $0.00055 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory
Structure
memory/daily_memory/YYYY.M.D/YYYY_M_D.md- Human-readable daily summary for one day.memory/daily_memory/YYYY.M.D/YYYY_M_D.json- Structured daily payload for code and downstream features.memory/weekly_memory/YYYY_M_D_to_YYYY_M_D/YYYY_M_D_to_YYYY_M_D.md- Weekly study plan generated from the last 7 daily summaries.memory/graphs/knowledge_graph.json- Knowledge-point graph.memory/graphs/error_graph.json- Error-pattern graph.memory/MEMORY.md- Auto-generated compatibility snapshot loaded into prompt context.memory/HISTORY.md- Append-only audit log of consolidation events.
Read Order
Prefer these sources in order:
- Daily
.jsonwhen you need structured fields such asdate,high_risk_knowledge_points,high_frequency_error_types,learning_status_summary, andtomorrow_study_suggestions. - Daily
.mdwhen you need a human-facing summary. - Graph JSON files when you need relationships, ranking, or historical nodes.
- Weekly
.mdwhen you need the next-week learning plan. HISTORY.mdonly when you need an audit trail of what was archived.
Graph Semantics
Knowledge graph:
- Nodes are knowledge points.
- Important fields include
time_points,risk,mastery,importance,last_seen, anddisplay_size. - Relations include prerequisite, similar, contains, and related links.
Error graph:
- Nodes are error patterns.
- Important fields include
error_count,severity,repeated,last_seen, anddisplay_size. - Relations include corresponding knowledge point, similar error, and correction suggestions.
Dynamic Adjustment Rules
- Low-frequency, low-risk, long-inactive nodes can be archived.
- Similar concepts should be merged upstream before adding too many nodes.
- Example items only keep recent representative samples; older examples are dropped automatically.
- Frontend views should size nodes by importance or severity, not raw node count.
Update Policy
- Do not manually edit
MEMORY.mdunless you are intentionally adjusting the compatibility snapshot. - Prefer updating the structured daily JSON or graph JSON when building new features.
- If both Markdown and JSON exist for the same day, trust the JSON as the machine-readable source.
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 · 57 lines · 13 tokens per session scan A 466b583d6179
memory is a skill published in the GitHub repository MathClaw-ruc/MathClaw (377 stars, last pushed 6mo ago), licensed MIT. It adds 13 tokens to every session and 551 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
self-improve-with-tinyfish
Enables Hermes to create new reusable skills for itself by researching live web sources with TinyFish Search and Fetch, analyzing source coverage, writing SKILL.md files, and installing them into Hermes memory. Use when the user asks Hermes to learn, teach itself, upgrade itself, or save a reusable capability.
flashcards
Spaced repetition flashcard system for learning. SM-2 algorithm, supports text and cloze deletion cards.
flow-next-audit
Audit .flow/memory/ entries against current code and keep, update, consolidate, replace, delete, or harden each. Use when asked to audit memory or graduate a recurring lesson into a gate.
learn-from-fix
Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learning, record a lesson, prevent a fixed mistake, or remember package guidance with --library.
mindos
MindOS: local knowledge assistant & shared KB. Keeps decisions, notes, SOPs, debugging lessons, research findings, preferences across sessions/agents. Core: save notes, search KB, organize files, run workflows, review, append CSV, hand off context, distill lessons. NOT for app source or paths outside KB. Triggers…
curate
Adds developer-authored annotations to the gauntlet knowledge base. Use when capturing tribal knowledge or rationale not visible in code.