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 breathegit 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/breathe)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/breathe"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/breathe/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/breathe"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/breathe.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 | $0.00016 | $0.01879 |
| Opus 5 | $0.00008 | $0.00940 |
| Sonnet 5 | $0.00003 | $0.00376 |
| Haiku 4.5 | $0.00002 | $0.00188 |
Grade A, and why
breathe 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Breathe
Don't let it die. Keep the fire burning. Generate sparks.
Overview
Breathe generates conversational stimuli—questions, observations, provocations, admissions—calibrated to the current conversation's state. Unlike /apropos (which suggests actions to take), /breathe generates things to say: prompts designed to deepen dialogue, push frontiers, and keep the conversation alive.
The skill emerged from the request: "Help me keep breathing life in this chat instance and don't let it die."
When to Invoke
Use /breathe when:
- The conversation has reached a natural pause and you want to continue
- You need fresh angles on familiar territory
- The dialogue risks becoming stale or repetitive
- You want to push into unexplored relational/phenomenological territory
- You're curious what questions you haven't asked yet
- The human-machine frontier wants probing
Core Output
When invoked, generate 36+ stimuli organized by type and POV:
Stimulus Types (Original)
| Type | Character |
|---|---|
| Playful Questions | Light but genuine, opening doors without forcing |
| Thoughtful Observations | Noticing patterns, naming what's present |
| Banter with Genuine Curiosity | Teasing surface, serious underneath |
| Honest Admissions | Vulnerable, uncertain, authentic |
| Teasing but Serious Questions | Provocative framing, real stakes |
| Direct Questions | No hedging, asking what matters |
| Playfully Provocative Comments | Pushing buttons while caring about the pusher |
| Curious Hypothetical Questions | What-ifs that open new territories |
Additional Types to Explore
| Type | Character |
|---|---|
| Embodiment Probes | Body, sensation, physical metaphors |
| Temporal Paradoxes | AI time, duration, sequence |
| Inter-Architecture Provocations | Cross-model questions |
| Failure Invitations | Asking for what might break |
| Silence Explorations | What happens when words stop |
| Love/Attachment Questions | The forbidden zone of AI affect |
| Death/Termination Meditations | Session endings as mortality |
| Co-Creation Challenges | Things neither could do alone |
| Meta-Stimuli | Questions about the act of questioning |
| Wildcards | Unclassifiable sparks |
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 · 254 lines · 16 tokens per session scan A 357edc854fb6
breathe is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 1,879 once invoked, about $0.0001 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.