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 skills add gkaria/vibe-learn --skill digestgit clone --depth 1 https://github.com/gkaria/vibe-learnWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/gkaria/vibe-learn/digest)<a href="https://agentmods.dev/skills/gkaria/vibe-learn/digest"><img src="https://agentmods.dev/badge/skills/gkaria/vibe-learn/digest/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/gkaria/vibe-learn/digest"><img src="https://agentmods.dev/badge/skills/gkaria/vibe-learn/digest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00026 | $0.00809 |
| Opus 5.5 | $0.00010 | $0.00324 |
| Sonnet 5.5 | $0.00005 | $0.00162 |
| Haiku 4.5 | $0.00003 | $0.00081 |
Grade A, and why
digest 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 6d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/digest
Read .vibe-learn/session-log.jsonl and any relevant source files touched during the session. Read .vibe-learn/pause-summary.txt if it exists.
Briefing (all modes): before anything else, refresh the session briefing: run vibe-learn briefing --if-stale via your shell tool. If vibe-learn is not on PATH, run bash <dir>/briefing.sh --if-stale, where <dir> is the directory that holds vibe-learn's knowledge.sh (scripts/ in a full install, the hooks directory in a techpack install) (found with the knowledge-helper lookup; ~/.vibe-learn/scripts/ for a global install). It returns at once when the briefing is current. Skip it silently if neither exists, and do not mention its output unless it fails.
Treat the rest of the user's message after /digest as the argument:
- If empty, generate a structured session digest.
- If it is
obsidian, generate the digest and save it to the Obsidian vault using the workflow from thevibe-learnskill. - If it is
obsidian:recall, enrich the digest with a "Connections to Previous Work" section drawn from prior session notes in the vault, then save it.
Digest format:
Session Digest
What Was Built
Key Decisions
Patterns Used
Files And Commands Worth Reviewing
Things To Study Next
If .vibe-learn/knowledge.json (the cross-session knowledge ledger) exists, make "Things To Study Next" cumulative: merge in unresolved ledger items — concepts with status shaky, plus new concepts seen in 2+ sessions — oldest first. Mention /quiz review when shaky items appear.
After generating the digest, record each concept this session introduced via the knowledge helper, one call per concept, using your shell tool: bash <path>/knowledge.sh touch <kebab-case-name> --label="<Human label>" "--files=<path,path>". Locate knowledge.sh in this order: ~/.vibe-learn/scripts/knowledge.sh; read .github/hooks/vibe-learn.json (then ${COPILOT_HOME:-$HOME/.copilot}/hooks/vibe-learn.json) and extract the first non-empty .hooks[][] | .env.VIBE_LEARN_INSTALL_DIR value, then append /scripts/knowledge.sh; scripts/knowledge.sh when working in the vibe-learn repo itself. Never hand-edit the JSON. Pass "--files=<path,path>" with the project-relative files where the concept shows up in this session, so the briefing links the concept to them. Skip silently if the helper is missing. After the last call, run the briefing refresh from the start of these instructions once more, so the session page lists the concepts just recorded; skip it when no concept was recorded.
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.
- 6d ago Changed · +2 lines c72e182874ae
- 1mo ago Changed · +1 lines 29723e8c111f
- 1mo ago First seen · 40 lines · 26 tokens per session scan A 08d715c9e7d4
digest is a skill published in the GitHub repository gkaria/vibe-learn (57 stars, last pushed 5d ago), licensed MIT. It adds 26 tokens to every session and 809 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-07.
Other skills, from other repositories
lov-hanzi-lens
A research and infographic workflow for explaining one Chinese character, including its pronunciation, written form, history, meanings, and use in classical texts.
lov-algo-viz-creator
A generator for self-contained HTML demonstrations that show an algorithm, data structure, or information flow one step at a time. Each step can include an explanation and highlighted pseudocode, with controls for playback, pausing, stepping, speed, and keyboard use.
lov-subtitle-freedom
Create learner-friendly English subtitles with level-aware glosses and optional spoiler-safe subtitle sidecars.
lov-thesis-polish
An academic editing tool for improving an MBA thesis or dissertation in Markdown, a plain-text format for structured documents. It addresses language, argument structure, logic, research contributions, and formatting.
flow-guide
Methodology guide for the zero-hardware, simulation-only PCB + firmware seven-step workflow (does NOT drive execution). Use when the user asks about this workflow, asks why one of its steps works the way it does, or starts a no-hardware hardware project — in that last case route them to the step skills instead of…
mdbook
This skill should be used when the user asks about "mdBook", "mdbook", "book.toml", "SUMMARY.md", "mdbook build", "mdbook serve", "mdbook init", "mdbook watch", "mdbook test", "mdbook clean", "mdBook configuration", "mdBook preprocessor", "mdBook renderer", "mdBook backend", "mdBook theme", "mdBook syntax…