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/abilityai/cornelius/manage-reference-datanpx skills add Abilityai/cornelius --skill manage-reference-datagit clone --depth 1 https://github.com/Abilityai/corneliusWhat 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 | $0.00088 | $0.01736 |
| Opus 5 | $0.00044 | $0.00868 |
| Sonnet 5 | $0.00018 | $0.00347 |
| Haiku 4.5 | $0.00009 | $0.00174 |
Grade A, and why
manage-reference-data 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manage Reference Data
Maintain a reference-kind scope — a non-core Brain/ layer of external facts/records the personal brain discovers bridges to, not a query store (a CRM owns queries). This skill upserts entity notes (overwrite-in-place), stamps the reference contract, and reindexes. It is generic: pass scope=<Folder> for any registered reference scope; Company is the default.
Read first: resources/layered-brains/REFERENCE-SCOPE-SCHEMA.md (the generic kind contract: frontmatter + linking + privacy) and the target scope's own schema doc for its type:/relationship: enum + structure (Company → COMPANY-BRAIN-SCHEMA.md, which also defines the family sub-scopes and the ref-* playbook suite this skill is the seed of). This skill enforces those docs; it does not restate them.
Hard rules (non-negotiable — these are what make it a reference scope):
- Every note gets
provenance: reference. Neveroriginated/endorsed/encountered/ai-inferred. - Reference notes are never crystallized, lifecycle-classified, or used as a synthesis-pulse source.
- Reference scopes are non-core → they never train q-values (the engine learn-gate already guarantees this; do not bypass it).
- Default read scope is unchanged. Reference data surfaces only under an explicit
BRAIN_READ_SCOPE=core,<Scope>mount.
Step 0 — Resolve the scope and confirm it is registered + reference-kind
cd resources/local-brain-search
SCOPE="${1:-Company}" # or parse scope=<Folder> from args
./venv/bin/python - "$SCOPE" <<'PY'
import sys, memory_config as mc
folder = sys.argv[1]
print("kind :", mc.scope_kind(folder))
print("is_reference :", mc.is_reference_scope(folder))
print("is_core :", folder in mc.CORE_FOLDERS)
PY
- If
is_referenceis False: the scope is not registered as reference. Stop and either (a) add aScopeDef(..., SCOPE_KIND_REFERENCE, False, (...))toSCOPE_REGISTRYinmemory_config.py, or (b)register_scope("<Folder>", kind="reference", slugs=(...)). See the schema doc → "Adding a new reference scope". Do not write entity notes into a non-reference folder.
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 · 118 lines · 88 tokens per session scan A 0f56c2d1ddce
manage-reference-data is a skill published in the GitHub repository Abilityai/cornelius (104 stars, last pushed 9d ago), licensed MIT. It adds 88 tokens to every session and 1,736 once invoked, about $0.0004 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…