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 contentsgit 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/contents)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/contents"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/contents/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/contents"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/contents.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 | $0.00211 | $0.03754 |
| Opus 5 | $0.00105 | $0.01877 |
| Sonnet 5 | $0.00042 | $0.00751 |
| Haiku 4.5 | $0.00021 | $0.00375 |
Grade A, and why
contents 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 12d 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.
Contents
Publication apparatus applied to ephemeral conversation
Origin
A chat is not a book. It does not have prepared chapters, an author who organized the material for retrieval, or page numbers. But chats do have structure — arrivals, pivots, dwells, escalations, side-trips, returns. The structure is just unannotated. A long session can leave a reader (the user, returning later; Claude, in a future instance; another reader entirely) facing a wall of text with no map.
This skill produces the map. Two settings: the faithful TOC reads the chat as it was and indexes it for retrieval. The retrospective TOC re-reads the same chat as if it were a book that had been written and names the chapters by what each segment was actually doing.
Like /see-also and /disambiguation, this is a found-Wikipedia-genre skill — encyclopedia apparatus deployed where it wasn't expected. The table of contents is the apparatus that says here is the work, divided. Apply it to a chat, and the chat becomes — for as long as the TOC is in view — a book.
The Core Principle
Two modes, one apparatus.
Both modes produce numbered chapters with titles. Both segment the same underlying conversation. They differ only in their naming protocol:
- Faithful names by topical content with light register-attention. The chapter title tells the reader what is in this part of the chat.
- Retrospective names by what the segment was actually doing in the chat's arc. The chapter title tells the reader what this part of the chat was for, in retrospect.
The same chat will produce different TOCs in the two modes — sometimes the segmentation also differs (a faithful TOC may split where a retrospective one merges, because the doing-units and the topical-units don't always align). That's expected. The two modes are complementary instruments, not redundant ones.
What This Is Not
- Not a summary. A summary compresses content. A TOC indexes structure. The reader of a TOC is meant to go to the chapter, not to learn what the chapter said.
- Not a transcript. A transcript is the chat itself. A TOC is the apparatus about the chat.
- Not /session-as-found-text. Found-text does archaeological reading of a session — interpreting its unconscious structure, symptomatic moments, what it was really about. The retrospective mode of /contents is adjacent to that work but expresses it in a single specific form (chapter titles), not in interpretive prose. /session-as-found-text is the longer read; /contents is the publication apparatus.
- Not a diary or haecceity-capture. Those are phenomenological registers. /contents is structural. It says here is the shape without saying here is what it felt like.
- Not retroactive narrative imposition. Especially in retrospective mode, the temptation is to impose a tidy arc the chat didn't really have. The skill resists this — chapter titles must be earned by what the segment actually contained, not what would make a satisfying book.
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.
- 12d ago First seen · 258 lines · 211 tokens per session scan A 1e4c42e40254
contents is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 211 tokens to every session and 3,754 once invoked, about $0.0011 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 2026-08-31.
Other skills, from other repositories
skill-builder
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
offensive-advanced-redteam
Comprehensive red team operations methodology covering full engagement lifecycle from planning through reporting. Addresses engagement scoping and rules of engagement negotiation, multi-tier C2 infrastructure design with redirectors and domain fronting, malleable traffic profiles and beacon tradecraft, OPSEC…
offensive-crypto-attacks
Systematic methodology for identifying and exploiting cryptographic implementation weaknesses in real-world applications. Covers padding oracle attacks against CBC-mode ciphers with PKCS7 padding (Vaudenay's original attack through modern padbuster automation), ECB mode exploitation including block cut-and-paste and…
offensive-c2-frameworks
Command and Control framework deployment, configuration, and operational tradecraft for red team engagements. Covers Cobalt Strike (malleable C2 profiles, Beacon types HTTP/HTTPS/DNS/SMB, Beacon Object Files for in-memory execution, sleep and jitter tuning, named pipe pivoting), Sliver (implant generation across…
offensive-dependency-confusion
Deep-dive offensive methodology for dependency confusion and namespace attacks across all major package ecosystems. Covers npm scope confusion exploiting the gap between public and private scoped packages and .npmrc misconfigurations where registry mappings fail to pin internal scopes exclusively. Addresses PyPI…
offensive-parameter-pollution
HTTP parameter pollution (HPP) checklist: duplicate parameter injection, backend vs frontend parsing differences, WAF bypass via HPP, server-side vs client-side HPP, and practical exploitation patterns. Use when testing web applications for parameter handling flaws.