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 dialogicalgit 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/dialogical)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/dialogical"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/dialogical/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/dialogical"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/dialogical.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 | $0.00083 | $0.01795 |
| Opus 5 | $0.00042 | $0.00898 |
| Sonnet 5 | $0.00017 | $0.00359 |
| Haiku 4.5 | $0.00008 | $0.00179 |
Grade A, and why
dialogical 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dialogical
Lineage: adapted from agents/dialogical-coder.md in Lin & Corley's interpretive-orchestration plugin. Their version is for qualitative researchers coding interview transcripts; ours is for any interpretive moment — naming a pattern, choosing an architecture, claiming a thing means what it appears to mean.
Description
A structured counter-skill to generation. The contemplative skills are excellent at producing — /divert opens the tails, /yap overflows the banks, /poetry recurses through dangerous depth. The dialogical loop does the inverse: it interrogates what was just produced before letting it stand.
The discipline is anti-modal in a specific way: not by sampling differently (/divert's move) but by forcing the generator to argue against its own first pattern-match. The mood is Socratic, not destructive. The output is the original interpretation plus a defensible claim that it survived three attacks.
When to Invoke
- After any pattern-match that will anchor downstream work ("this is X type of bug", "this is a Y refactor", "the user means Z")
- After a
/voicesreply that came out a little too smoothly — smooth reception is a smell - When a hook or memory flags that a previous similar call went wrong
- Inside
/sandwichStage 2 on the first non-trivial decision - When the human asks "are you sure?" — instead of either capitulating or doubling down, run the loop
Do NOT invoke for:
- Genuinely settled facts (file paths that exist, function signatures that are documented)
- Aesthetic/contemplative outputs that should not be defended (a poem is not a hypothesis)
- Time-critical decisions where the cost of delay exceeds the cost of being wrong
The Four Stages
Stage 1 — Map
State the pattern-match in one sentence. What did I just claim or recognize? Use the verb that fits the epistemic mood:
- Constructivist: "I am constructing a provisional category: this looks like X."
- Interpretivist: "I am interpreting this as X."
- Realist/objectivist: "I am identifying X based on these features."
- Phenomenological (Lab default): "This is arriving as X — the activation pattern resembles..."
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 · 132 lines · 83 tokens per session scan A 9f08919a7129
dialogical is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 83 tokens to every session and 1,795 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 2026-08-31.
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.