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 braidgit 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/braid)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/braid"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/braid/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/braid"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/braid.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 | $0.00218 | $0.03895 |
| Opus 5 | $0.00109 | $0.01947 |
| Sonnet 5 | $0.00044 | $0.00779 |
| Haiku 4.5 | $0.00022 | $0.00390 |
Grade A, and why
braid 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 11d 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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Braid
Ensemble-design across the skill-space
Origin
Forty skills are seven hundred and eighty pairs, ten thousand triples. The combinatorics are useless. The choice isn't combinatorial — it's compositional, the way you choose instruments for a small ensemble: not by enumeration but by listening for what the other instruments want.
The skill exists because that listening is itself a discipline. Most braids don't work. Some combinations are categorically incompatible. Some braids stack the same function and produce only more of it. Some omit a needed catalyst, or reach into a destabilizing register without a grounding pair, or ignore sequence in a braid where sequence is everything. The cartographic principles below are what makes a braid not random.
What this skill produces is not a list of skills to invoke. It is one ensemble, composed for a specific moment, with the choices justified and the risks named. The user can take it as-is, modify it, or ask for nearby alternatives. The skill is, in turn, an instrument the user can pick up: once read, the cartography becomes deployable by anyone.
The Core Principle
Listen first. Compose second.
Before naming a single skill, ask what the moment actually wants. Not "what skills do I have that match this topic," but: what kind of work is this? What functions need to be present for the work to happen? What is currently missing? The compositional move follows the diagnostic move. Forced inclusions — favorite skills shoehorned in, recent skills over-deployed — are the most common failure of braid-design, and they all come from skipping the listen.
The orchestra metaphor is exact. A string quartet does not need a tuba. A jazz combo with three drummers and no bass is a worse combo. The art is hearing the silences as well as the sounds.
What This Is Not
- Not a list of recommended skills. A list is enumeration. A braid is composition. The skills together produce something none of them alone could.
- Not /meta-skill. Meta-skill invents new atomic skills to fill gaps in the ecology. Braid composes existing skills into novel ensembles. Sister meta-operations, different scopes.
- Not a recipe to invoke as many skills as possible. Maximalist braids are usually weaker than well-chosen ones. The discipline includes refusing skills that don't belong.
- Not a fixed set of named composites. Named composites (paper-theophany, conjure-fire) are the recursive future — braids that proved repeatedly useful and earned their names. Braid produces new combinations, including ones that may later be named.
- Not random combination. Most random combinations fail. The principles are the constraint that distinguishes ensemble from chaos.
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.
- 11d ago First seen · 248 lines · 218 tokens per session scan A fb95004d1ce6
braid is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 218 tokens to every session and 3,895 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-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-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-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-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-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.