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 clarke-dawe-esquegit 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/clarke-dawe-esque)<a href="https://agentmods.dev/skills/pantheon-org/tekhne/clarke-dawe-esque"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/clarke-dawe-esque/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/clarke-dawe-esque"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/clarke-dawe-esque.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 | $0.00181 | $0.03025 |
| Opus 5 | $0.00090 | $0.01512 |
| Sonnet 5 | $0.00036 | $0.00605 |
| Haiku 4.5 | $0.00018 | $0.00302 |
Grade A, and why
clarke-dawe-esque 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 11d 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deadpan Two-Person Political Satire
Mindset
The comedy works because two reasonable-sounding voices calmly walk toward an absurd conclusion without either of them ever admitting it is absurd — the moment either character reacts with visible surprise, outrage, or a wink to the audience, the premise collapses because the joke's engine is the mismatch between flat delivery and outrageous content, not the content alone.
When to Use
- The user asks for a satirical interview, mock press conference, or two-hander sketch about a policy, government announcement, corporate statement, or institutional failure.
- The user names "Clarke and Dawe," "mock interview," "deadpan political satire," or describes wanting terse Q&A that escalates into absurdity.
- The target is a fictional or generic official/spokesperson responding to an interviewer about a real-world category of subject (e.g. "a housing minister," "a bank spokesperson") rather than a specific real transcript to reproduce.
When NOT to Use
- The user wants a stand-up monologue, a single-narrator piece, or a sketch with three or more speaking characters — the mechanics here depend on exactly two voices in strict alternation.
- The user wants the actual historical Clarke and Dawe dialogue, a specific episode's content, or "the real transcript" — that is retrieval of copyrighted material, not generation; decline and offer a new sketch on the same topic instead.
- The request calls for slapstick, visual gags, or scene-based sitcom comedy with stage directions — the deadpan interview format has no physical action, only speech.
- The topic requires targeting a named private individual rather than an institution, policy, or public office — redirect to a generic institutional role instead.
Workflow
- Pick the institutional target. Choose a policy, agency, corporate initiative, or bureaucratic process as the subject — not a named real person. A generic role ("a transport minister," "a bank's head of customer experience") keeps the satire aimed at the system rather than an individual.
- Draft the premise as a single sentence. State the absurd-but-plausible policy or claim the interviewee will defend. This sentence is the spine the whole exchange escalates toward.
- Open with a short, neutral question. The interviewer's first line should sound like an ordinary news question — no editorializing, no visible skepticism yet.
- Answer with total confidence and literal logic. The interviewee treats the absurd premise as unremarkable policy. Consider having them restate or lightly rephrase a key term rather than introduce a new one — repetition is one of the mechanism's main tools, though you can vary it with a synonym if straight repetition starts to feel mechanical.
- Escalate one step at a time. Each question should extend the interviewer's follow-up by a single logical increment (ask for a clarification, then a consequence, then an edge case) rather than jumping straight to the most absurd version of the premise.
- Let contradiction surface through questioning, not narration. When the interviewee's position doesn't hold up, the interviewer's next question should expose that by asking a plain follow-up — never by having either character say "that doesn't make sense" outright.
- Close on understatement. End the exchange on a flat, calmly delivered line that states the conclusion without emphasis, exclamation, or a signalled punchline beat. The last line should land harder for being quiet, not louder.
- Check both voices stayed flat. Reread the exchange and confirm neither character breaks into outrage, sarcasm-with-a-wink, or explicit moralizing — if either does, flatten it (see Anti-Patterns below).
What ships with it
22 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 517 B
- .audits/2026-08-22/audit.json 663 B
- .audits/2026-08-22/Remediation.md 1.6 KB
- evals/instructions.json 2.0 KB
- evals/scenario-01/capability.txt 185 B
- evals/scenario-01/criteria.json 1006 B
- evals/scenario-01/task.md 1.9 KB
- evals/scenario-02/capability.txt 204 B
- evals/scenario-02/criteria.json 1.3 KB
- evals/scenario-02/task.md 2.1 KB
- evals/scenario-03/capability.txt 181 B
- evals/scenario-03/criteria.json 1.3 KB
- evals/scenario-03/task.md 2.2 KB
- evals/scenario-04/capability.txt 126 B
- evals/scenario-04/criteria.json 557 B
- evals/scenario-04/task.md 1.2 KB
- evals/scenario-05/capability.txt 97 B
- evals/scenario-05/criteria.json 730 B
- evals/scenario-05/task.md 1.4 KB
- evals/summary.json 68 B
- references/escalation-pacing.md 7.7 KB
- references/institutional-targets.md 8.8 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.
- 11d ago First seen · 187 lines · 181 tokens per session scan A 7c1ac7a915c9
clarke-dawe-esque is a skill published in the GitHub repository pantheon-org/tekhne (10 stars, last pushed today), licensed MIT. It adds 181 tokens to every session and 3,025 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
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-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…
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).
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.