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/robinslange/learning-loop/gapsnpx skills add robinslange/learning-loop --skill gapsgit clone --depth 1 https://github.com/robinslange/learning-loopWhat 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 | $0.00094 | $0.02914 |
| Opus 5 | $0.00047 | $0.01457 |
| Sonnet 5 | $0.00019 | $0.00583 |
| Haiku 4.5 | $0.00009 | $0.00291 |
Grade A, and why
gaps scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gaps: Epistemic Gap Analysis
Overview
The vault grows by accumulation. /gaps shakes the cage. It surfaces tensions, questions absences, and flags thin ice. The truth doesn't need to defend itself: weak beliefs get questioned, strong beliefs get stress-tested.
When to Use
/gaps "topic": focused analysis on a specific topic/gaps: auto-picks the densest unchallenged cluster in the vault/gaps --sweep: runs across all major domain clusters
Parameters
Parse from the invocation. All have defaults.
| Parameter | Options | Default |
|---|---|---|
| topic | any string | auto-pick if absent |
| depth | shallow / medium / deep |
scales to note maturity |
| sweep | flag | off |
| dry-run | flag | off |
Depth auto-scaling:
- Permanent notes → deep
- Fleeting notes → medium
- Inbox notes → shallow
- Mixed maturity → use the highest
Provenance
This skill emits provenance events for pipeline observability. Run each Bash command silently.
At session start (after scope identified):
node "${CLAUDE_PLUGIN_ROOT}/scripts/provenance-emit.js" '{"agent":"gaps","skill":"gaps","action":"session-start","intent":"TOPIC","config":{"depth":"DEPTH"}}'
At session end:
node "${CLAUDE_PLUGIN_ROOT}/scripts/provenance-emit.js" '{"agent":"gaps","skill":"gaps","action":"session-end","notes_analysed":N,"counterpoints_created":N,"rewrites":N,"thin_ice":N,"tensions":N,"blindspots":N}'
Per-note tracking is handled automatically by the PostToolUse hook.
Process
Step -1: Parameter Resolution
No arguments (/gaps):
Run auto-pick immediately (find the densest unchallenged cluster — see Step 0). After presenting results, mention the alternatives in one line:
Analysed [cluster]. Alternatives:
/gaps "topic"for a specific domain,/gaps --sweepacross all clusters,--depth shallow|medium|deepto override maturity scaling.
Topic provided (/gaps "topic"):
Proceed immediately. Depth auto-scales to note maturity.
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 · 258 lines · 94 tokens per session scan A 3fa12e37db54
gaps is a skill published in the GitHub repository robinslange/learning-loop (11 stars, last pushed 11d ago), licensed Apache-2.0. It adds 94 tokens to every session and 2,914 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 2026-08-30.
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…