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/agentsystemlabs/nebula/project-termsnpx skills add AgentSystemLabs/nebula --skill project-termsgit clone --depth 1 https://github.com/AgentSystemLabs/nebulaWhat 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 | $0.00183 | $0.03436 |
| Opus 5 | $0.00092 | $0.01718 |
| Sonnet 5 | $0.00037 | $0.00687 |
| Haiku 4.5 | $0.00018 | $0.00344 |
Grade A, and why
project-terms 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nebula keeps a shared, committed glossary at TERMS.md (repo root). Every agent reads it before
starting and speaks in its terms — see AGENTS.md. Your job here is to keep it true after the task you
just finished, so the next agent and the next teammate call things by the same name you did.
The MEMORY LOG records what happened; TERMS.md records what things are called. Do not put a work log
in the glossary, and do not put definitions in the work log.
Detect every session, promote only what recurred
A TERM is a name the team actually uses. A name that appeared once — coined in one reply, one commit, one session's design — is a guess at a name, and a glossary that takes every guess fills up with rows nobody says twice, stops being scannable, and stops being trusted. So this skill runs in two tiers:
- Sightings — every task, notice the vocabulary it surfaced: a thing that got a name, a word the user typed for a thing, a name you used in a reply, a commit, or a MEMORY LOG entry. Sightings are cheap and you record all of them.
- Promotion — a concept becomes a TERM (a row in a numbered section) only when it has been used in
more than one separate task. Until then it waits in the Candidates ledger at the bottom of
TERMS.md, with where it was seen.
"Separate task" means a different MEMORY LOG entry, a different session, or a different commit from the one that first sighted it. You coining a name in your reply and then writing it in your own commit is one sighting. The user typing it in a later prompt, a later task's memory entry using it, or a later commit message using it is the second — and that is what promotes it.
Two shortcuts, both the user's call, not yours: if the user says "name this", "add this to terms", or "promote X", promote on the spot; and if the user names a thing in their prompt that has no TERM, that is still only a first sighting — the TERM comes when they, or a later task, use it again.
What lands immediately
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 · 186 lines · 183 tokens per session scan A b7a520d1fb84
project-terms is a skill published in the GitHub repository AgentSystemLabs/nebula (100 stars, last pushed 2d ago), licensed MIT. It adds 183 tokens to every session and 3,436 once invoked, about $0.0009 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…