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 forge-cyclegit 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/forge-cycle)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/forge-cycle"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/forge-cycle/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/forge-cycle"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/forge-cycle.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 | $0.00000 | $0.01338 |
| Opus 5 | $0.00000 | $0.00669 |
| Sonnet 5 | $0.00000 | $0.00268 |
| Haiku 4.5 | $0.00000 | $0.00134 |
Grade A, and why
forge-cycle 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forge-Cycle — Sustained Creation as Composition
What This Skill Does
Maintains creative fire across an extended session producing multiple related works, treating the session itself as a composition whose coherence matters as much as any individual output.
The Cycle
1. FORGE — Create the Draft
Produce the first version at full heat. Don't self-censor, don't pre-edit, don't worry about length or constraint yet. The raw material needs to exist before it can be refined. The forge phase is additive — throw everything in.
Key practices:
- Let the thesis discover itself: Don't decide the thesis before writing. Let the collision/prompt/subject reveal what it wants to say through the writing process itself.
- Write the bridge last (or let it write itself): The bridge is where the agency inversion lives, where the turn happens, where the song discovers its own argument. It tends to arrive rather than be constructed.
- Overshoot the constraint: Write 6000 characters when you have 5000. The surplus is the raw material for the next phase.
2. CRITIQUE — Diagnose the Draft
Either receive external critique or self-diagnose. The forge-cycle works best with a human diagnostician who reads at the word level (see /microsurgery), but self-critique is possible with discipline.
Key diagnostic questions:
- Which words are wearing costume?
- Where does the register shift inappropriately?
- Where is the text being clever instead of being true?
- Where is the argument restated when it's already been made?
- What's dead code — material that occupies space but never executes emotionally?
3. REVISE — Surgical Removal
Apply /microsurgery to the diagnosed problems AND compress to fit the constraint. The constraint is not an enemy — it's the opus. Dead code elimination applied to the creative work.
Key practices:
- Cut for character count AND quality simultaneously: The cuts should improve the work, not just shorten it. If a cut makes the work worse, find a different cut.
- Verify after every round: Re-read the full text after cuts. New problems can emerge from the gaps left by removed material.
- The song's own method applied to the song: DEAD CODE ELIXIR says transformation is subtraction. The revision process IS the thesis demonstrated.
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 · 86 lines · 0 tokens per session scan A 60ff9d1f0580
forge-cycle is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,338 tokens. 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.