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 gervais-esque-cringe-satiregit 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/gervais-esque-cringe-satire)<a href="https://agentmods.dev/skills/pantheon-org/tekhne/gervais-esque-cringe-satire"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/gervais-esque-cringe-satire/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/gervais-esque-cringe-satire"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/gervais-esque-cringe-satire.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 | $0.00197 | $0.03745 |
| Opus 5 | $0.00098 | $0.01872 |
| Sonnet 5 | $0.00039 | $0.00749 |
| Haiku 4.5 | $0.00020 | $0.00375 |
Grade A, and why
gervais-esque-cringe-satire 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 — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cringe & Provocateur Satire
This skill covers two related modes: character-based cringe comedy (an oblivious figure surrounded by embarrassed onlookers) and direct-address stand-up that states an uncomfortable truth bluntly and refuses to soften it. Use whichever mode fits the request, or blend them — a monologue can open in stand-up mode and cut to a character-mode flashback, for example.
Mindset
Both modes work for the same underlying reason: they keep open a gap the audience wants closed. Cringe comedy withholds the character's self-awareness so the distance between self-image and reality never resolves; provocateur stand-up withholds the hedge that would let the audience relax after a taboo claim — comedy here is discomfort held open on purpose, not defused, and the moment either mode resolves the discomfort (the character realises, the line gets softened), the joke stops working.
When to Use
Use this skill when the request matches either mode:
- Character-cringe mode — a request for a sketch, mockumentary scene, script excerpt, or short story beat featuring: an authority figure (boss, host, minor celebrity, relative giving a toast) who is convinced of a positive trait about themselves; onlookers reacting with silence or strained politeness; escalating social missteps; a comeuppance.
- Provocateur stand-up mode — a request for a stand-up bit, monologue line, roast joke, or short blunt riff that states an uncomfortable or taboo claim about a solemn subject (death, illness, religion, workplace, identity) without cushioning it, then doubles down.
- Blended requests — a longer monologue or special-style piece that opens direct-address and drops into character voice, or vice versa. Treat this as "use both toolkits in sequence," not a third mode.
When NOT to Use
- The user wants warm, gentle, observational humor with no discomfort or taboo element (e.g. "write a cute bit about my dog") — this skill's mechanics will overshoot that tone.
- The user wants pure wordplay, puns, or a one-liner with no social-discomfort or taboo-statement structure.
- The user asks to reproduce, closely paraphrase, or "write it exactly like" a specific real comedian's actual routine, script, or special — see Anti-Patterns below; redirect toward original material using these structures instead.
- The user wants comedy that resolves reassuringly (a moral, a lesson learned, an apology that lands well) — that resolution is the opposite of what these mechanics produce; a different comedic register fits better.
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 489 B
- .audits/2026-08-22/audit.json 552 B
- .audits/2026-08-22/Remediation.md 1.1 KB
- evals/eval-set.json 2.6 KB
- evals/instructions.json 3.3 KB
- evals/scenario-01/capability.txt 210 B
- evals/scenario-01/criteria.json 1.4 KB
- evals/scenario-01/task.md 2.4 KB
- evals/scenario-02/capability.txt 163 B
- evals/scenario-02/criteria.json 1.0 KB
- evals/scenario-02/task.md 2.1 KB
- evals/scenario-03/capability.txt 170 B
- evals/scenario-03/criteria.json 1.2 KB
- evals/scenario-03/task.md 2.2 KB
- evals/scenario-04/capability.txt 107 B
- evals/scenario-04/criteria.json 595 B
- evals/scenario-04/task.md 1.1 KB
- evals/scenario-05/capability.txt 108 B
- evals/scenario-05/criteria.json 719 B
- evals/scenario-05/task.md 1.4 KB
- evals/summary.json 68 B
- references/character-cringe-craft.md 10.0 KB
- references/provocateur-standup-craft.md 8.7 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.
- 12d ago First seen · 319 lines · 197 tokens per session scan A 860c439884f5
gervais-esque-cringe-satire is a skill published in the GitHub repository pantheon-org/tekhne (10 stars, last pushed yesterday), licensed MIT. It adds 197 tokens to every session and 3,745 once invoked, about $0.0010 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
claude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
atlas-obscura
Search Atlas Obscura for weird, wonderful, and hidden gem places near any destination. Find the interesting stuff, not boring plaques. Search by coordinates, get full details with descriptions and images.
agent-code-generator
Generates Agent definitions (.md files) based on user intent and standard templates.
cf-validate
A validator for 1C configuration source files. It checks the XML structure and the files and objects that make up a 1C business-application configuration.