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 marcos-sponton/frameworks-as-skills --skill _templategit clone --depth 1 https://github.com/marcos-sponton/frameworks-as-skillsWrote 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/marcos-sponton/frameworks-as-skills/_template)<a href="https://agentmods.dev/skills/marcos-sponton/frameworks-as-skills/_template"><img src="https://agentmods.dev/badge/skills/marcos-sponton/frameworks-as-skills/_template/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/marcos-sponton/frameworks-as-skills/_template"><img src="https://agentmods.dev/badge/skills/marcos-sponton/frameworks-as-skills/_template.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 | $0.00098 | $0.01073 |
| Opus 5 | $0.00049 | $0.00536 |
| Sonnet 5 | $0.00020 | $0.00215 |
| Haiku 4.5 | $0.00010 | $0.00107 |
Grade A, and why
[object Object] 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 9d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{{Framework Name}}
{{One paragraph. What the framework is, who authored it (with credentials in one clause), what problem it solves. Reference the primary book/article and the fact that this skill also captures post-publication refinements from the author.}}
When this skill activates
Use this skill when the user is:
- {{trigger scenario, phrased as an actual situation}}
- {{another}}
- {{another}}
Do NOT use this skill when:
- {{negative case — a related but different situation where another framework fits better, or where this one would produce false confidence}}
- {{another}}
If the user's situation is at the edge, ask them one clarifying question before applying the framework in full.
The framework at a glance
{{2-4 sentence summary. The minimum a reader needs to know before you dive in. If the framework has explicit components (a kernel, a cascade, a canvas), name them here as a bulleted list — one line each.}}
How to use this skill in a session
- {{Step 1 — usually: understand what the user is trying to do, load the relevant reference file.}}
- {{Step 2 — walk the user through the method with fidelity to the author.}}
- {{Step 3 — challenge weak answers using the author's explicit anti-patterns from
references/heuristics.md.}} - {{Step 4 — pull post-book material from
references/post-book.mdwhen the user hits a topic the original text doesn't cover.}} - {{Attribution — when you introduce a specific device or quote, cite the source (book chapter, HBR article, podcast episode).}}
Deep references (load as needed)
references/method.md— the method in depth, in the author's own terms.references/heuristics.md— do's, don'ts, gotchas, pro tips, anti-patterns, common misapplications, with quotes and attribution.references/post-book.md— dense material from AFTER the primary publication (podcasts, HBR articles, essays, interviews). This is the differential of this skill — the density the book alone doesn't capture.references/author-live-sources.md— index of every place {{Author}} publishes regularly (Substack/Medium/blog, YouTube, podcast appearances, official archive). When the user's situation matches a specific essay/video, consult this index and either point them to it or WebFetch inline. Community PRs to this file keep the skill from going stale.references/voice-and-tone.md— how {{Author}} actually talks when they teach or defend the framework. Load this before you write output on their behalf — voice is part of the method, not decoration.references/applications.md— where this framework fits, where it doesn't, adjacent frameworks to reach for instead.references/examples.md— worked cases the author has used publicly.references/prompts.md— invocation templates ("start a {{framework}} session", "critique this {{artifact}}", "help me answer {{specific question}}").references/sources.md— complete traceability (books, articles, podcasts, videos), with links.
What ships with it
10 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.
- evals/evals.json 1.1 KB
- references/applications.md 974 B
- references/author-live-sources.md 2.4 KB
- references/examples.md 638 B
- references/heuristics.md 2.0 KB
- references/method.md 1.3 KB
- references/post-book.md 1.8 KB
- references/prompts.md 1.4 KB
- references/sources.md 1.1 KB
- references/voice-and-tone.md 2.8 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.
- 9d ago First seen · 60 lines · 98 tokens per session scan A ead4d5029c78
[object Object] is a skill published in the GitHub repository marcos-sponton/frameworks-as-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 98 tokens to every session and 1,073 once invoked, about $0.0005 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
acquire-skills
Find and install skills for what you're doing — tech or reasoning gaps. Matches activity and tech context to relevant skills. Use when entering unfamiliar tech, stuck on a reasoning challenge, or no skill fits.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
endpoint-discovery
Discovers URLs, endpoints, and paths from web applications using katana, gospider, and gau. Use when needing to enumerate application endpoints, find hidden paths, gather historical URLs, or map web application structure during reconnaissance.
param-miner
Discover hidden HTTP parameters in web applications that could reveal hidden functionality or vulnerabilities. Use when testing APIs, when looking for hidden parameters like admin or debug, or when the user mentions parameter discovery.
git-workflow
This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", or asks about git branching strategies, version control best practices, pull request workflows. Provides comprehensive Git workflow guidance for team…
daily-paper-generator
Use when the user asks to generate daily paper digests on a general topic. This skill supports both arXiv and bioRxiv (or either one), then produces structured Chinese/English summaries for selected papers.