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/grburgess/mindgap/second-brainnpx skills add grburgess/mindgap --skill second-braingit clone --depth 1 https://github.com/grburgess/mindgapWhat 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 | $0.00100 | $0.00583 |
| Opus 5 | $0.00050 | $0.00292 |
| Sonnet 5 | $0.00020 | $0.00117 |
| Haiku 4.5 | $0.00010 | $0.00058 |
Grade A, and why
second-brain 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 yesterday.
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.
What it actually says
second-brain
The graph has an analytic layer (mindgap mine / mindgap_mine_*) on top of plain
retrieval. Math proposes cheap candidates; you adjudicate. Read AGENTS.md first for the ingest
rules. mentions=0.25 is hygiene, not the precision lever.
Pick the mode by intent
- enrich — grounding a topic you're working on.
mindgap_mine_enrich(seed)returns the RWR-ranked relevant subgraph (reaches 2-3 hops, unlike 1-hop context). Read-only. - learn — deciding what to study/ingest next.
mindgap_mine_learn()ranks the thin spots (stubs, isolated/fresh-thin papers, in-demand-thin concepts) and writesfrontier.jsonfor the{{TOPICS}}loops. Read-only. - connect — growing the graph with latent links.
mindgap_mine_connect(k)returns guarded candidate pairs + both bodies + shared support. Gated write-back (below).
connect adjudication rubric (math proposes, you dispose)
For each candidate, read both bodies. Accept only if you can state the specific relationship in
one sentence from the bodies — a nameable relationship, not mere co-occurrence. Otherwise reject.
Per accepted pair choose rel (relates_to default; depends_on/implements/cites/part_of/
defines when the bodies justify it) and set confidence (0.5–0.8 for a new unverified link).
Gated write-back
Never raw-insert. Write confirmed links via mindgap_ingest with created_by="mine:connect".
For a genuinely distant accepted pair (the candidate's distant flag), also synthesize a bridging
insight node (type=concept, created_by=mine:connect, body = the one-line rationale with
[[a]] [[b]] wiki-links). Show the batch before committing. Re-running is idempotent — already-linked
pairs are skipped. (CLI equivalent: mindgap mine connect --apply decisions.json.)
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.
- yesterday First seen · 36 lines · 0 tokens per session scan A 78901ff69717
second-brain is a skill published in the GitHub repository grburgess/mindgap (0 stars, last pushed 1mo ago), licensed MIT. It adds 100 tokens to every session and 583 once invoked, about $0.0005 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 2026-08-31.
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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.