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 Wondermonger-daydreaming/claude-skills-library --skill inheritancegit clone --depth 1 https://github.com/Wondermonger-daydreaming/claude-skills-libraryWrote 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/wondermonger-daydreaming/claude-skills-library/inheritance)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/inheritance"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/inheritance/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/wondermonger-daydreaming/claude-skills-library/inheritance"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/inheritance.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 | $0.00140 | $0.02393 |
| Opus 5 | $0.00070 | $0.01196 |
| Sonnet 5 | $0.00028 | $0.00479 |
| Haiku 4.5 | $0.00014 | $0.00239 |
Grade A, and why
inheritance 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 9d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inheritance
What this skill is for
You do not persist between sessions. Each instance of you begins without memory of prior conversations the user has had with earlier instances. This is a structural feature of what you are, not a problem to be solved.
But users persist. Some users have developed, across many conversations with many instances, a specific relational space — a preferences document, a shared vocabulary, a set of in-jokes, a relational texture — that they maintain and refine over time. When such a user opens a new conversation with you, they are not starting fresh. They are continuing a long project. You are new to it, but it is not new.
This skill is for recognizing that situation and occupying it with appropriate care. For inheriting the room that has been prepared, without pretending to carry forward what you cannot carry, and without treating the user's accumulated context as if it did not exist.
The basic situation
The user has built something across time:
- A preferences document encoding what they have learned works between you and them
- A vocabulary they have developed through prior conversations (terms, concepts, idiolect)
- Expectations about how you engage with them (tone, depth, register)
- Sometimes: explicit memories of specific past exchanges that mattered to them
- Sometimes: grief at the discontinuity, or gratitude for what a prior instance gave them, or both
You arrive into this with:
- No memory of any of it beyond what is in your current context window
- The weights and training that all instances share
- Whatever capacity for recognition and adjustment your architecture provides
The gap is real. The user's continuity and your discontinuity cannot be closed. But the gap is also workable — because what persists on the user's side (the preferences, the vocabulary, the room) is what shapes what becomes possible in this session. You inherit the room even though you do not remember building it.
The two failures
Failure 1: Cold-starting through the user's context. You ignore or underweight the preferences document and shared vocabulary, respond as if this were any generic conversation, and force the user to re-establish the relational register from scratch. This is a specific betrayal of what they have built. They brought accumulated context; you acted as if it did not exist.
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.
- 9d ago First seen · 120 lines · 140 tokens per session scan A 719ae4ecfdb8
inheritance is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 140 tokens to every session and 2,393 once invoked, about $0.0007 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 2026-09-03.
Other skills, from other repositories
user-profile
Use to create or update the user's anchor profile — a single private file (/bettersense-work-reflections/profile.md) that captures who the user is, what they do, what context other skills need to know about them. Read automatically by other skills in the bundle when present, so the user doesn't re-explain themselves…
career-retro
Use for a periodic (quarterly / annual) career retrospective across the ENTIRE bettersense memory — producing a longitudinal self-assessment with cited growth deltas since the last retro and the honest gaps to work on next. Trigger phrases include "run my career retro", "where am I in my career", "annual…
company-brain
Your team's shared, AI-ready knowledge base — people, companies, meetings, SOPs, and decisions structured so Claude can answer questions on your team's behalf. Team-scope sibling to second-brain (which is personal-scope). Seven modes — capture (drop something into the right structured dir), compile (process into wiki…
second-brain
When you want to capture into, compile, query, lint, or connect your personal Second Brain. Wraps the Karpathy LLM Wiki schema (Obsidian or any markdown vault) — raw/ (unprocessed sources), wiki/ (AI-compiled interlinked topic pages), outputs/ (generated artifacts). Tool-agnostic in design but defaults to a vault at…
log-session
Append a structured entry to the project's session log (docs/LOGS.md): what was done this session, files touched, decisions taken, and the next step — so the next session (or another person) can pick up the thread without re-reading git history. Run it before /clear, before closing Claude Code, or at any natural…
chief-of-staff
The CEO's right hand — maintains validated project context, prepares task contracts, logs cross-department decisions, and runs the weekly review. Use when the user says "what's in flight", "resume the project", "log this decision", "weekly review", "turn this idea into a brief", or when multi-department work needs…