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 commands/rashadansari/myagents/remembergit clone --depth 1 https://github.com/RashadAnsari/myagentsWrote 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/commands/rashadansari/myagents/remember)<a href="https://agentmods.dev/commands/rashadansari/myagents/remember"><img src="https://agentmods.dev/badge/commands/rashadansari/myagents/remember.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 | $0.00014 | $0.00647 |
| Opus 5 | $0.00007 | $0.00324 |
| Sonnet 5 | $0.00003 | $0.00129 |
| Haiku 4.5 | $0.00001 | $0.00065 |
Grade A, and why
remember 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task
Save one or more durable memories using the agent-memory MCP server.
Subject: $ARGUMENTS
Step 1: Determine what to remember
If $ARGUMENTS is not empty, use it as the subject. Enrich it with any relevant details from the current conversation: decisions made, conventions stated, preferences expressed, gotchas discovered, or architecture facts established. Produce a concrete, specific memory content (at least 40 characters) - do not store the raw argument text verbatim if it is vague.
If $ARGUMENTS is empty, scan the full conversation history and identify every durable learning from this session worth storing. A learning is durable if a future agent in a fresh session would benefit from it. Skip anything temporary, vague, or already obvious from reading the code. If nothing qualifies, tell the user and stop.
Step 2: Classify each item as project or user memory
For each item, decide scope using this rule:
- Project memory - the fact is meaningful only in this repository: architecture decisions, code conventions, non-obvious workflow steps, dependency quirks, recurring bug root causes, gotchas, testing requirements, or handoff notes.
- User memory - the fact applies regardless of which project you are in: coding preferences, global conventions, background context, tool choices, communication style, or recurring behavioral patterns.
When in doubt: if removing the project would make the fact meaningless, it is project memory. If it still applies anywhere, it is user memory.
Step 3: Get the project root (for project memories only)
If any item is classified as project memory, run:
git rev-parse --show-toplevel
Store as PROJECT_ROOT.
Step 4: Store each memory
For project memory, call project_remember (agent-memory MCP server) with:
project_root: value ofPROJECT_ROOTcontent: specific, concrete content - at least 40 characters, no secrets, no command outputsource:"user"if the user explicitly told you,"agent"if you inferred it
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 · 54 lines · 14 tokens per session scan A ed33037f972f
remember is a command published in the GitHub repository RashadAnsari/myagents (6 stars, last pushed 27d ago), licensed MIT. It adds 14 tokens to every session and 647 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
memorise
Digest files/folders into local, token-free graph memory (Memorised them All).
recall
Recall from local graph memory — returns a tiny, citable slice (token-free).
export-memory
Export the generated memory as portable Markdown files.
forget
Delete a project's local memory (Memorised them All) — irreversible.
memory-status
Check the local stack (deterministic engine, Tesseract, MarkItDown) and projects.
kiro-steering-custom
Command "kiro-steering-custom" from gotalab/cc-sdd, covering kiro custom steering creation, workflow, available templates, steering principles and tool guidance.