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/tallesborges/zdx/memorynpx skills add tallesborges/zdx --skill memorygit clone --depth 1 https://github.com/tallesborges/zdxWhat 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 | $0.02220 |
| Opus 5 | $0.00023 | $0.01110 |
| Sonnet 5 | $0.00009 | $0.00444 |
| Haiku 4.5 | $0.00005 | $0.00222 |
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 3d 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory
Use ZDX's native memory tools and the user's markdown notes under $ZDX_MEMORY_ROOT.
This skill is about routing, note-saving, and filing conventions. It is not the search implementation and does not replace Memory_Search / Thread_Search.
Follow the existing note structure you find in memory.
Paths
- Memory root:
$ZDX_MEMORY_ROOT - Notes:
$ZDX_MEMORY_ROOT/Notes - Calendar:
$ZDX_MEMORY_ROOT/Calendar - Memory index:
$ZDX_MEMORY_ROOT/Notes/MEMORY.md
Memory discovery is backed by ZDX's native SQLite index. Prefer memory tools before raw file searches.
- Use
$ZDX_MEMORY_ROOTdirectly in tool arguments. - Treat
$ZDX_MEMORY_ROOTas a container directory, not a note location. - Do not create
.mdfiles directly under$ZDX_MEMORY_ROOT; useNotes/for regular notes andCalendar/for period notes. - Ignore
@Archive/and@Trash/unless the user asks. - Do not guess alternate memory locations; derive from
$ZDX_MEMORY_ROOT.
Default workflow
- Check the embedded
<memory_index>block to find likely notes. - Use
Memory_Searchfor discovery across exported threads, notes, and calendar files. - Open the hits you care about:
readthepathfor notes and calendar,Read_Threadthethread_idfor threads. - Answer directly, or edit the relevant note with
apply_patch. - When saving memory, write full detail to a note first, then decide whether
MEMORY.mdneeds a concise pointer.
Tool patterns
Search memory
Use Memory_Search for open-ended memory discovery. It searches the native memory index for:
- exported conversation threads
- canonical notes under
$ZDX_MEMORY_ROOT/Notes - canonical calendar files under
$ZDX_MEMORY_ROOT/Calendar
Search by names, project terms, decisions, URLs, paths, commands, errors, or distinctive phrases. Do not manually slug note paths or guess filesystem names; let search return the path.
Start with a focused natural-language query and a small limit. Prefer limit:5-10, then open the best 1-3 hits. If results are weak, run a second search with synonyms, aliases, acronyms, or the likely project/person name.
What ships with it
2 files 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.
- 3d ago First seen · 231 lines · 46 tokens per session scan A 74e4f3ccf80b
memory is a skill published in the GitHub repository tallesborges/zdx (20 stars, last pushed 4d ago), licensed MIT. It adds 46 tokens to every session and 2,220 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…