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 skills/bobbyjohnstx/tinycode/remembernpx skills add bobbyjohnstx/tinycode --skill remembergit clone --depth 1 https://github.com/bobbyjohnstx/tinycodeWhat 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 | $0.00046 | $0.00824 |
| Opus 5 | $0.00023 | $0.00412 |
| Sonnet 5 | $0.00009 | $0.00165 |
| Haiku 4.5 | $0.00005 | $0.00082 |
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 2d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Remember
Use this skill at a natural session boundary when you need to decide what knowledge is worth persisting beyond this conversation.
When to Use
Use this skill when:
- The user says "remember", "save this", "keep that", or "what should we keep from this session"
- A session surfaced a durable fact, user preference, project convention, or decision with rationale worth persisting
- You are wrapping up a work session and want to distill what graduates from chat history into memory
- The user wants to clean up stale or conflicting memory entries
When Not to Use
- The user wants a quick scratch note for this session only — use a notepad or inline note instead
- The user wants to directly edit
CLAUDE.mdorAGENTS.md— do that edit directly, do not run a triage workflow - Mid-task capture of working state — wait for a natural review point; mid-task memories are usually temporary
- The information is already captured in
CLAUDE.mdor derivable from the code — do not duplicate it
Examples
Good: "We just figured out the deploy pipeline uses a non-standard port — remember that" → Classify as a durable project fact, route to project memory with source context.
Good: End of session: "What should we save from today?" → Scan the session, classify each candidate, propose destinations.
Bad: "Jot down that I want to try Exa for search" → That is a scratch note, not a durable memory. Keep it in the conversation or a quick note.
Bad: "Update CLAUDE.md with the new build command" → Edit CLAUDE.md directly. Do not run a triage workflow for a direct instruction update.
Goal
Promote durable, reusable knowledge into the right memory surface instead of leaving it buried in chat history.
Memory surfaces
~/.config/tinycode/projects/<project>/memory/— durable project knowledge (facts, feedback, decisions)CLAUDE.md/AGENTS.md— durable instructions and conventions when they truly belong there- Session notes — temporary working context for the current conversation only
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.
- 2d ago First seen · 77 lines · 46 tokens per session scan A 9e0b598dff04
remember is a skill published in the GitHub repository bobbyjohnstx/tinycode (11 stars, last pushed 4d ago), licensed MIT. It adds 46 tokens to every session and 824 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
system-prompts
Write system prompts, tool docs, and agent definitions. Project tag conventions + RFC 2119 keywords + dense compression. Use when authoring or editing any prompt the model reads.
tool-prompt-optimization
Optimize the description prompts an AI agent reads to learn its built-in tools (the .md files under prompts/tools/). Two halves: (1) measure how much of a prompt is already inferable from the tool's JSON parameter schema + name, to prune redundancy with evidence; (2) house authoring rules for what belongs in a tool…
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
archon-cli
Drive Archon through its CLI: run AI workflows on a repo, manage those runs (inspect, approve, reject, cancel, resume), set up Archon or change its config, author new workflows, and improve workflow prompts. Use when the user says "use archon", "run archon", "archon workflow", "fix issue #N with archon", "have archon…
semantic-compression
Re-encode verbose prose into a dense telegraphic register — punctuation as connectives, label frames, verbless assertions — without losing normativity or precision. Use when compressing system prompts, tool/function descriptions, skill bodies, or agent instructions; reducing token count or context bloat; making…
greet
A greeting skill for testing.