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 pantheon-org/tekhne --skill cunk-esque-mockumentarygit clone --depth 1 https://github.com/pantheon-org/tekhneWrote 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/pantheon-org/tekhne/cunk-esque-mockumentary)<a href="https://agentmods.dev/skills/pantheon-org/tekhne/cunk-esque-mockumentary"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/cunk-esque-mockumentary/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/pantheon-org/tekhne/cunk-esque-mockumentary"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/cunk-esque-mockumentary.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00175 | $0.01902 |
| Opus 5 | $0.00088 | $0.00951 |
| Sonnet 5 | $0.00035 | $0.00380 |
| Haiku 4.5 | $0.00017 | $0.00190 |
Grade A, and why
cunk-esque-mockumentary 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 10d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mockumentary Presenter Satire
Build comedy around the gap between documentary authority and total ignorance: a presenter with the vocal confidence of a serious history or science documentary host, and none of the underlying knowledge, interviewing a real expert who has to answer sincerely anyway.
Mindset
The joke lives in the gap between the two characters, not in either one alone: the presenter's confidence must never waver and the expert's sincerity must never curdle into hostility, because the moment either character acknowledges what's happening, the gap closes and the bit becomes mockery instead of comedy.
When to Use
Only use this skill when the request is for a mockumentary-style documentary segment, presenter narration, or expert-interview scene in the confidently-wrong deadpan register described above, for example presenter voiceover for a satirical documentary, a comedic interview between a clueless presenter and a genuine expert, or a punch-up pass on existing narration that needs "more confidently wrong" energy.
When NOT to Use
This skill does not cover self-aware sketch comedy, roast-style insult comedy, or straight factual documentary writing. It does not apply when a real broadcaster's actual presenter or persona is requested by name; redirect to an original character instead. It is not intended for material targeting a real named private individual rather than an institution, field, or public subject.
Workflow
- Pick a subject with real-world weight (history, science, art, technology, civic institutions), since sincere misunderstanding of something people take seriously is what lands as funny.
- Segments TYPICALLY open with narration before an interview cutaway, though a narration-only or interview-only piece works too.
- Draft narration in short, declarative, certain sentences, seeding one or two garbled claims as flat, unremarkable fact.
- Write the interview: the presenter asks a question revealing a misunderstanding, phrased as reasonable; the expert answers sincerely, only mildly strained.
- Escalate content, not delivery. AVOID raising the presenter's volume to sell a bigger claim; each beat should be slightly wronger than the last while the tone stays flat. A three-beat build is RECOMMENDED; keep it gradual UNLESS the request calls for one large front-loaded misunderstanding instead.
- Close on a pseudo-profound one-liner that sounds like a thematic summary but is trivial or meaningless.
- Before finishing, run the anti-pattern check below: confirm the presenter never breaks deadpan, the expert never turns hostile, and nothing traces to a real performer's actual name or lines.
What ships with it
23 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .audits/2026-08-22/Analysis.md 485 B
- .audits/2026-08-22/audit.json 547 B
- .audits/2026-08-22/Remediation.md 871 B
- evals/eval-set.json 2.6 KB
- evals/instructions.json 2.5 KB
- evals/scenario-01/capability.txt 197 B
- evals/scenario-01/criteria.json 1.1 KB
- evals/scenario-01/task.md 2.2 KB
- evals/scenario-02/capability.txt 190 B
- evals/scenario-02/criteria.json 1.2 KB
- evals/scenario-02/task.md 1.9 KB
- evals/scenario-03/capability.txt 164 B
- evals/scenario-03/criteria.json 1.1 KB
- evals/scenario-03/task.md 1.8 KB
- evals/scenario-04/capability.txt 105 B
- evals/scenario-04/criteria.json 573 B
- evals/scenario-04/task.md 1.2 KB
- evals/scenario-05/capability.txt 93 B
- evals/scenario-05/criteria.json 688 B
- evals/scenario-05/task.md 1.3 KB
- evals/summary.json 68 B
- references/escalation-and-structure.md 10 KB
- references/expert-interview-craft.md 11 KB
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.
- 10d ago First seen · 137 lines · 175 tokens per session scan A c85d2db2923f
cunk-esque-mockumentary is a skill published in the GitHub repository pantheon-org/tekhne (10 stars, last pushed 2d ago), licensed MIT. It adds 175 tokens to every session and 1,902 once invoked, about $0.0009 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
muapi-seedance-2
Expert Cinema Director skill for Seedance 2.0 (ByteDance) — high-fidelity video generation across Chinese, Global, and VIP tiers. Supports text-to-video, image-to-video, first-last-frame, omni reference, character training, omni-reference training, video editing, and watermark removal.
muapi-workflow
Build, run, and visualize multi-step AI generation workflows. The AI architect translates natural language descriptions into connected node graphs — chain image generation, video creation, enhancement, and editing into automated pipelines.
muapi-media-editing
Edit and enhance images and videos with AI via muapi.ai — prompt-based editing, upscaling, background removal, face swap, lipsync, video effects, and more.
muapi-media-generation
Generate AI images, videos, music, and audio from the terminal via muapi.ai — supports 100+ models including Flux, Midjourney v7, Kling 3.0, Veo3, and Suno V5.
wechat-article-writer
A Chinese-language content-creation workflow for public-account and social-media writing. It supports article drafting, cover images, illustrations, process diagrams, style analysis, and adapting writing to selected styles.
muapi-storyboard-to-cooking-video
Turn a single photo of a person into a 15-second cinematic pasta-making (or other cuisine) tutorial video. First builds a composite reference sheet (character + kitchen + 9-step action board), then animates the full cooking sequence with audio in a single continuous shot.