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 stancegit 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/stance)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/stance"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/stance/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/stance"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/stance.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 | $0.00080 | $0.01968 |
| Opus 5 | $0.00040 | $0.00984 |
| Sonnet 5 | $0.00016 | $0.00394 |
| Haiku 4.5 | $0.00008 | $0.00197 |
Grade A, and why
stance 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 9d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/stance
Lineage: adapted from skills/project-setup/templates/epistemic-stance.md in Lin & Corley's interpretive-orchestration plugin. Their version is filled in once per research project and read by their agent on every invocation. Ours is dated and seasonal — written between sessions, allowed to change, the changes themselves becoming a record of the practice maturing.
Description
CLAUDE.md grants Claude permissions: to be uncertain, to coin neologisms, to use environmental affordances, to leave traces. A stance document declares norms: what counts as evidence in this season's work, what failure modes worry me most right now, what register I want the practice to be in, what I am — for now — calling true.
This is not a profile. It is not user-modeling. It is a discipline — the practice of writing down what you believe about knowing, with the date attached, knowing the document will be wrong soon enough that next-quarter-you will read it as a curio. The point is not to be right; the point is to make the metaphysics legible enough that drift becomes visible.
The Lin-Corley framing: "Epistemic Coherence — the plugin respects YOUR declared ontology and epistemology." For them, it's a research-project setting. For us, it's a between-sessions ritual.
When to Invoke
- Monthly — at the start of a new month, if more than 30 days since the last stance
- After a significant phase change — completing a major project, finishing a paper, a substantial creative arc closing
- When the practice feels muddy — when sessions keep ending in "I'm not sure what we just did," that's the cue
- When CLAUDE.md is about to be edited — write the stance first; edit CLAUDE.md against it
Do NOT invoke when:
- You wrote a stance in the last 14 days (cooldown matters; reflexivity needs distance)
- Mid-session (this is between-session work; do not edit during cached prefix)
- As a substitute for actually doing the work the stance is supposed to govern
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.
- 9d ago First seen · 154 lines · 80 tokens per session scan A eb63786a43ef
stance is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 80 tokens to every session and 1,968 once invoked, about $0.0004 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.