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 PGHH84/claude-layered-learning --skill wrap-upgit clone --depth 1 https://github.com/PGHH84/claude-layered-learningWrote 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/pghh84/claude-layered-learning/wrap-up)<a href="https://agentmods.dev/skills/pghh84/claude-layered-learning/wrap-up"><img src="https://agentmods.dev/badge/skills/pghh84/claude-layered-learning/wrap-up/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/pghh84/claude-layered-learning/wrap-up"><img src="https://agentmods.dev/badge/skills/pghh84/claude-layered-learning/wrap-up.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 | $0.00050 | $0.01874 |
| Opus 5.5 | $0.00020 | $0.00750 |
| Sonnet 5.5 | $0.00010 | $0.00375 |
| Haiku 4.5 | $0.00005 | $0.00187 |
Grade A, and why
wrap-up 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 1mo 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Wrap-Up
Run four phases in order:
Ship ItRemember ItReview & ApplyDiary Capture
Present a consolidated report at the end. Do not add a final push prompt.
Model Selection
Wrap-up is mechanical work. Use the cheapest capable model available.
Hard Safety Boundaries
- never create repo-local runtime memory folders in working repositories
- never treat generated home-directory mirrors as the editable source of repo-local guidance
- in this public repo, repo
CLAUDE.mdis the local guidance surface - never edit
~/.claude/CLAUDE.mdor~/.codex/AGENTS.mddirectly when a generated mirror path should be used - never write arbitrary
~/.codex/**state outside the approved global mirror-sync path - never auto-apply global canonical edits or new-skill changes without approval
- never do speculative doc edits, speculative file moves, or destructive cleanup
Runtime Paths
- project memory:
~/.claude/projects/<slug>/memory/MEMORY.md - diary output:
~/.claude/memory/diary/ - reflections:
~/.claude/memory/reflections/ - project operating guidance source: repo
CLAUDE.md - global operating guidance source:
~/.agents/global/PROJECT.md - generated global mirrors:
~/.claude/CLAUDE.md,~/.codex/AGENTS.md - optional personal extension:
~/.claude/skills/wrap-up/personal.md
Path-To-Slug Transform
Use this exact transform so wrap-up, /diary, /reflect, and the
PreCompact hook agree on project identity:
- If inside a git repository, resolve the canonical project root with
git rev-parse --show-toplevel. - If that repo root contains
/.worktrees/, strip the/.worktrees/<name>suffix and use the parent repo path as the canonical project root. - Otherwise, if not inside a git repository, use the canonical absolute working directory.
- Resolve symlinks before deriving the slug.
- Replace every
/in the canonical absolute path with-.
Phase 1: Ship It
Documentation sync
- Review the diff in each repo touched during the session.
- If the change affects project-maintained docs such as README, changelog, setup guides, runbooks, or verification docs, update only the documents directly affected.
- If no project-maintained docs were directly affected, skip this step.
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.
- 1mo ago First seen · 207 lines · 50 tokens per session scan A 8d134590853d
wrap-up is a skill published in the GitHub repository PGHH84/claude-layered-learning (2 stars, last pushed 7mo ago), licensed MIT. It adds 50 tokens to every session and 1,874 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
Migrate
Intakes external content (notes, CLAUDE.md, Cursor rules, Obsidian/Notion/Apple Notes exports), classifies chunks against the LifeOS taxonomy, and commits with provenance after confidence-tiered approval. USE WHEN /migrate, migrate content, import from other LifeOS, bring in old notes, import Cursor rules, import…
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
Profile
View, edit, or clear the LifeOS User Model (PRINCIPALIDENTITY.md) — persistent identity context loaded at session startup. Three intents: View, Edit (identity, goals, constraints, preferences), Clear (reset). Read by Algorithm OBSERVE and skills for personalization. USE WHEN profile, show profile, view profile, who am…
wiki-dashboard
Create dynamic, queryable Obsidian dashboard views using Bases or Dataview. Use for auto-updating tables, indexes, or structured views of vault content; not for ordinary question answering.
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.
session-compact
AI DevKit · Compact a historical AI coding session with Jev when context is long, work is handed off or resumed, or durable continuation facts and memory candidates need extraction.