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/ilyagorsky/memory-toolkit/parknpx skills add IlyaGorsky/memory-toolkit --skill parkgit clone --depth 1 https://github.com/IlyaGorsky/memory-toolkitWrote 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/ilyagorsky/memory-toolkit/park)<a href="https://agentmods.dev/skills/ilyagorsky/memory-toolkit/park"><img src="https://agentmods.dev/badge/skills/ilyagorsky/memory-toolkit/park.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 | $0.00020 | $0.00567 |
| Opus 5 | $0.00010 | $0.00283 |
| Sonnet 5 | $0.00004 | $0.00113 |
| Haiku 4.5 | $0.00002 | $0.00057 |
Grade A, and why
park 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/park — Park an idea
Quickly save an idea/task from the current session to pick up in the next one. Does not close the session — only captures the thought.
Step 1: Determine what to park
From the argument or from the context of recent messages, determine:
- What — the essence of the idea/task (1-2 sentences)
- Why — what problem it solves
- Workstream — which workstream it belongs to (from
workstreams.jsonor a new one) - Context — key details from the current conversation that would be lost without recording
If unclear — ask the user briefly.
Step 2: Choose where to save
By priority:
- Existing workstream file — if the idea belongs to an active workstream, append to its file
- New file in ideas — if it's a new topic:
---
name: {short name}
description: {one line — for search via memory.js}
type: project
---
## What
{essence}
## Why
{problem it solves}
## Context
{key details from the conversation}
## Next step
{what to do when you come back to this}
- Quick note — if the idea is raw and has no structure:
node $MEM/memory.js note "{essence of the idea}"
Step 3: Propose & confirm
MUST show the user what will be saved and where BEFORE writing anything:
Park this?
What: {essence}
File: {path}
Workstream: {name}
Save? (yes/skip)
Wait for explicit confirmation. Do NOT write until the user confirms.
Step 4: Write
After confirmation:
- Write the file (Step 2 format)
- If a new file was created — add a line to the MEMORY.md index
- Show receipt:
Parked: {name}
File: {path}
Pick up: /session-start {workstream}
Rules
- Do not close the session — the user continues working
- Do not duplicate — if the idea is already in backlog or memory, point out where
- Context from the conversation matters more than wording — better to record it raw than to lose it
- One park = one idea. If there are multiple — offer to park them one by one
- If the user did not provide an argument — suggest the last discussed topic
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 · 91 lines · 20 tokens per session scan A 99588e18f0c6
park is a skill published in the GitHub repository IlyaGorsky/memory-toolkit (13 stars, last pushed 4mo ago), licensed MIT. It adds 20 tokens to every session and 567 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 2026-08-30.
Other skills, from other repositories
acontext-installer
Install Acontext, Login & Init Acontext Project, Add Skill Memory to Agent.
init
Initialize structured context for this project. Scaffolds .scs/ with all 11 concern bundles, scans the project, and recommends where to start.
context-ingest
The single entry point for getting anything new into your context architecture. Takes any input (documents, URLs, YouTube, meeting notes, pasted content) and triages it: dump to inbox, park in planned, or integrate into active docs. WHEN TO USE: "Here's a document — integrate it into my context" "Save this for later"…
context-audit
Audits context architecture for CLEAR compliance, boundary enforcement, and consistency. WHEN TO USE: User says "audit context for CLEAR" User asks "check for duplication across data points" User requests "find boundary violations in [area]" Planning restructuring work Before adding new data points (cleanup existing…
context-routing
Cross-zone retrieval and task-driven bundle resolution for BCOS. /context search ranks docs across every zone in one shared schema; /context bundle (P5) returns a curated, freshness-flagged, source-of-truth-aware context bundle for a declared task. Mechanical-first; LLM is opt-in via --semantic / --resolve-conflicts /…
context-mine
Extracts structured context from conversation exports (Slack, meeting transcripts, chat logs) into inbox for processing.