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 agentmods add skills/pantheon-org/tekhne/monty-python-esquenpx skills add pantheon-org/tekhne --skill monty-python-esquegit clone --depth 1 https://github.com/pantheon-org/tekhneWhat 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 | $0.00197 | $0.02119 |
| Opus 5 | $0.00098 | $0.01059 |
| Sonnet 5 | $0.00039 | $0.00424 |
| Haiku 4.5 | $0.00020 | $0.00212 |
Grade A, and why
monty-python-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 3d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Monty Python-esque Comedy
Mindset
The comedy in this tradition is not randomness dressed up as "weird": it is absolute internal consistency applied to an impossible premise. A sketch is funny because the characters treat the absurd with the same procedural seriousness they'd give a tax return, and the escalation follows rules the audience can half-predict a beat before the logic breaks something. If you remember one thing: escalate the logic, don't escalate the randomness.
When to Use
Only use this skill when the request is for new, original material built on an ordinary premise pushed to absurd extremes, not for retrieving or lightly disguising existing content.
- The user asks for an original sketch, script, or short comic bit ("write me a sketch about...", "give me a scene where...", "a bit involving...").
- The premise is ordinary (a council meeting, a customer complaint, a job interview, a queue), and the user wants it pushed to absurd extremes through dialogue.
- The user wants dry, escalating, deadpan-toned comedy rather than punchline-driven one-liners.
- The user references Monty Python's style or tradition as a tone descriptor, not as a request to retrieve or adapt specific existing material.
When NOT to Use
- The user asks for the actual text of an existing Monty Python sketch, or a "rewrite"/"parody" of one that keeps its characters, structure, or catchphrases recognisable. If the user wants to reuse recognisable characters or catchphrases, do not attempt a lightly disguised version; offer new, premise-driven material inspired by the same mechanism instead (see Anti-Patterns).
- The user wants slapstick, physical-comedy description, observational stand-up material, roast jokes, or punchline-per-line sitcom banter: those rely on delivery and timing, not on escalating premise logic, and this skill's techniques will not fit the brief.
- The user wants comedy about a real, named, identifiable person in a way that could read as mockery of them specifically rather than of the absurd situation.
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 481 B
- .audits/2026-08-22/audit.json 544 B
- .audits/2026-08-22/Remediation.md 1.0 KB
- evals/instructions.json 2.3 KB
- evals/scenario-01/capability.txt 215 B
- evals/scenario-01/criteria.json 1.4 KB
- evals/scenario-01/task.md 2.1 KB
- evals/scenario-02/capability.txt 177 B
- evals/scenario-02/criteria.json 1.5 KB
- evals/scenario-02/task.md 1.9 KB
- evals/scenario-03/capability.txt 193 B
- evals/scenario-03/criteria.json 1.4 KB
- evals/scenario-03/task.md 2.2 KB
- evals/scenario-04/capability.txt 117 B
- evals/scenario-04/criteria.json 572 B
- evals/scenario-04/task.md 1.2 KB
- evals/scenario-05/capability.txt 114 B
- evals/scenario-05/criteria.json 725 B
- evals/scenario-05/task.md 1.6 KB
- evals/summary.json 68 B
- references/deadpan-delivery-and-abrupt-endings.md 5.1 KB
- references/escalation-and-bureaucratic-engines.md 6.2 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.
- 3d ago First seen · 175 lines · 197 tokens per session scan A 80f8c6be4d9a
monty-python-esque is a skill published in the GitHub repository pantheon-org/tekhne (10 stars, last pushed 8d ago), licensed MIT. It adds 197 tokens to every session and 2,119 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
bigquery-ai-ml
Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics. Use when you need to write SQL queries that perform time-series forecasting, predict values, detect outliers or anomalies, find key drivers, perform semantic search or vector search, classify text, calculate similarity…
edge-to-edge
Use this skill to migrate your Jetpack Compose app to add adaptive edge-to-edge support and troubleshoot common issues. Use this skill to fix UI components (like buttons or lists) that are obscured by or overlapping with the navigation bar or status bar, fix IME insets, and fix system bar legibility.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
comet-github
将 Comet GitHub 维护请求路由到基于证据的 PR 审阅、Issue 分诊、本地想法收集、CI 诊断或 Issue 实施流程。用户提到 Comet GitHub Issue/PR 但未指定流程，或询问下一步如何处理时使用。.
cfe-patch-method
Генерация и актуализация перехватчика метода в расширении 1С (CFE). Используй когда нужно перехватить метод заимствованного объекта — вставить код до, после, вместо оригинала, изменить его тело (ИзменениеИКонтроль) — или актуализировать перехватчик после изменения оригинала.
southwest
Search Southwest Airlines fares and points pricing via Patchright browser automation. SW is not in any GDS or API. Covers all fare classes, Companion Pass value, and fare drop monitoring.