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 rjmurillo/ai-agents --skill using-forgetful-memorygit clone --depth 1 https://github.com/rjmurillo/ai-agentsWrote 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/rjmurillo/ai-agents/using-forgetful-memory)<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/using-forgetful-memory"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/using-forgetful-memory.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 | $0.00117 | $0.02025 |
| Opus 5 | $0.00059 | $0.01012 |
| Sonnet 5 | $0.00023 | $0.00405 |
| Haiku 4.5 | $0.00012 | $0.00202 |
Grade A, and why
using-forgetful-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 4d 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 — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using Forgetful Memory
Forgetful is a semantic memory system using Zettelkasten (atomic note) principles. This skill guides effective memory usage.
When to Query Memory
Query memory proactively when:
- Starting work on a project (check for existing context)
- User references past work, decisions, or discussions
- Encountering a problem that may have been solved before
- Implementing patterns that may already be documented
- Needing context about preferences or approaches
Use execute_forgetful_tool("query_memory", {...}) with:
query: Natural language search termsquery_context: Why you're searching (improves ranking)include_links: true (to see connected knowledge)
Getting Recent Memories for a Project
To see what's been recorded recently for a specific project:
execute_forgetful_tool("get_recent_memories", {
"limit": 10,
"project_ids": [PROJECT_ID]
})
This is useful when:
- Starting a session on a project you haven't worked on recently
- Reviewing what was captured in previous conversations
- Getting a quick overview of project knowledge
When to Create Memory
Create memories for knowledge worth preserving:
- Important decisions with rationale (importance 8-9)
- Technical patterns or approaches (importance 7-8)
- Architectural choices (importance 9-10)
- Preferences and workflows (importance 8-9)
- Project milestones (importance 6-7)
- Solutions to non-trivial problems (importance 7-8)
Do NOT create memories for:
- Temporary context (current file paths, transient issues)
- Common knowledge available elsewhere
- Trivial or throwaway information
- Content that changes frequently
Atomic Memory Principles
Each memory must pass the atomicity test:
- Can you understand it at first glance?
- Can you title it in 5-50 words?
- Does it represent ONE concept/fact/decision?
Constraints
| Field | Limit | Guidance |
|---|---|---|
| Title | 200 chars | Short, searchable phrase |
| Content | 2000 chars | Single concept (~300-400 words) |
| Context | 500 chars | WHY this matters |
| Keywords | 10 max | For semantic clustering |
| Tags | 10 max | For categorization |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 273 lines · 117 tokens per session scan A ce4f835fb8ce
using-forgetful-memory is a skill published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed today), licensed MIT. It adds 117 tokens to every session and 2,025 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
context-recovery
Recover missing conversation context after explicit compaction or truncation, or when the user explicitly asks to recover prior work. Use for requests such as "where were we before compaction?" when the current thread is insufficient. Do not trigger on a generic "continue" when the current thread already provides an…
context-search
A continuity workflow for finding context from earlier coding-agent sessions. It can inspect continuation notes and session records when a task refers to previous work.
abmind-runtime-operations
Inspect and maintain abmind memory, persona files, sleep, backups, encryption, and runtime health.
memory-search
Search persistent memory for facts, decisions, and past conversations.
topic-save
Save and manage topic-specific knowledge files from conversations.
meditation
Consolidate session learning into permanent architecture — extract patterns into skills, instructions, prompts, or memory.