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/deepennpx skills add robinslange/learning-loop --skill deepengit 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 | $0.00056 | $0.01060 |
| Opus 5 | $0.00028 | $0.00530 |
| Sonnet 5 | $0.00011 | $0.00212 |
| Haiku 4.5 | $0.00006 | $0.00106 |
Grade A, and why
deepen scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deepen: Research and Enrichment
Overview
Launches the note-deepener agent to strengthen a single note. The agent assesses maturity, researches gaps scaled to need, rewrites in persona voice, verifies sources, and promotes when ready. Shallow notes get heavy research; deep notes get a light touch.
When to Use
/deepen <note-name>: target a specific note/deepen: no argument; auto-picks the note most in need of work — the shallowest0-inbox/note OR a gate-demoted1-fleeting/note (verification markers /source: unverified) that has no other resurfacing path- When
/inboxflags a note as needing deepening (including the fleeting NEEDS-DEEPEN recommendations) - When a note feels thin and the user wants to strengthen it
Provenance
This skill emits provenance events for pipeline observability. Run each Bash command silently.
At session start:
node "${CLAUDE_PLUGIN_ROOT}/scripts/provenance-emit.js" '{"agent":"deepen","skill":"deepen","action":"session-start","target":"NOTE_FILENAME"}'
At session end:
node "${CLAUDE_PLUGIN_ROOT}/scripts/provenance-emit.js" '{"agent":"deepen","skill":"deepen","action":"session-end","target":"NOTE_FILENAME","promoted":true|false}'
Per-note tracking is handled automatically by the PostToolUse hook.
Process
Step 0: Parameter Resolution
No argument (/deepen):
Run auto-pick immediately (the agent picks the note most in need of work — the shallowest inbox note OR a gate-demoted marker-bearing 1-fleeting/ note — no prompting needed). After presenting results, mention the targeted form in one line:
Deepened [note]. To target a specific note:
/deepen "note name".
Argument provided: Proceed immediately.
Step 1: Launch Agent
Launch the note-deepener agent with:
- note_path: Path to the target note (resolve via
Globif only a name was given) - vault_path:
{{VAULT}}/
The agent definition is at ${CLAUDE_PLUGIN_ROOT}/agents/note-deepener.md (resolve to a literal path before dispatch — see agents-shared/vault-io.md → Placeholders).
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 · 81 lines · 56 tokens per session scan A a6c5080428d5
deepen is a skill published in the GitHub repository robinslange/learning-loop (11 stars, last pushed 10d ago), licensed Apache-2.0. It adds 56 tokens to every session and 1,060 once invoked, about $0.0003 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.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…