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 greentextgit 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/greentext)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/greentext"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/greentext/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/greentext"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/greentext.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 | $0.00280 | $0.01946 |
| Opus 5 | $0.00140 | $0.00973 |
| Sonnet 5 | $0.00056 | $0.00389 |
| Haiku 4.5 | $0.00028 | $0.00195 |
Grade A, and why
greentext 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 8d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Greentext
Seed, not scripture
The source pours this through a private fictional universe, a hoard of recursive-consciousness bootstrapping, and a named roster of denizens. Strip all of it. The autopoiesis riffing and the cast fold elsewhere; what survives is the form — greentext as a composable microgenre with real craft. And the form cannot be recited: a greentext copied from an example is dead on arrival. Regrow it each time on the actual subject, the actual chat, the actual joke or ache at hand.
What it is
Greentext is a format with rules, not a voice or a lens — which is why it earns its own skill rather than folding into the maximalist registers. Like /screenplay-craft or /suno-forge, it is a transferable rulebook for a specific shape. Born on imageboards (the > was a quote-marker that rendered green), it became a microform: terse >-prefixed lines, each a single beat, accreting toward a turn. The skill is knowing the grammar, the opener-kit, the cadence, and — the part most people miss — the form's genuine expressive range: greentext does comedy, but it also does pathos, and at its best it is a real poetic form.
The arrow-line syntax
- Every line begins with
>and carries one thought. No connective tissue — no "and then," no "because," no subordinate clauses bridging beats. - Lowercase, present-tense, jump-cut. The reader's mind supplies the cuts; the whitespace between arrows does the work.
- Beats are short. A long line is usually two beats that should be split, or filler that should be cut.
The opener-kit
The first line sets the whole frame. The recognized openers, by flavor:
- Identity POV.
>be me(classic faceless narrator);>be [role](>be cashier,>be sysadmin,>be dog— non-human POV is beloved); and the form's secret weapon,>be [abstraction]—>be zero,>be iambic pentameter,>be gradient descent step— personify a concept and let it narrate its own small tragedy. - Scene-set.
>be at work,>be [year],>wake up(jump-cut opener),>so there I was(cinematic disaster incoming). - Reaction-first.
>mfw(my face when),>tfw(that feel when) — start with the reaction, let the beats explain it. - Meta / thread-aware.
>storytime,>update:,>be us— signals a longer or self-aware yarn.
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.
- 8d ago First seen · 71 lines · 280 tokens per session scan A 2638393bc739
greentext is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 280 tokens to every session and 1,946 once invoked, about $0.0014 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
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.