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 ai-driven-dev/framework --skill distributiongit clone --depth 1 https://github.com/ai-driven-dev/frameworkWrote 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/ai-driven-dev/framework/distribution)<a href="https://agentmods.dev/skills/ai-driven-dev/framework/distribution"><img src="https://agentmods.dev/badge/skills/ai-driven-dev/framework/distribution/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/ai-driven-dev/framework/distribution"><img src="https://agentmods.dev/badge/skills/ai-driven-dev/framework/distribution.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 | $0.00104 | $0.00988 |
| Opus 5 | $0.00052 | $0.00494 |
| Sonnet 5 | $0.00021 | $0.00198 |
| Haiku 4.5 | $0.00010 | $0.00099 |
Grade A, and why
distribution 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 4d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Distribution
distribution is a leaf: it depends on kernel only, and knows no tool and no manifest. It
answers exactly one question — where does content come from, and how is it fetched — for
whoever asks. framework is the only context that reaches it (framework → distribution); a
plugin's own content and how it gets translated are someone else's job once it has arrived here.
What goes in
| Concept | Location |
|---|---|
| A marketplace registration (name, source, scope, staleness) | domain/marketplace.ts, domain/marketplace-source-mode.ts |
| A cached catalog fetch | domain/ports/marketplace-cache.ts |
| The plugin catalog shape | domain/catalog.ts (the Claude-shaped parser lives here too) |
| A reader for a non-Claude catalog shape | domain/catalog-parsers/ |
| A port this context's callers hold | domain/ports/ — registry, cache, trust-store, catalog-repository, fetcher, raw-catalog-fetcher |
| Add / list / refresh / register / resolve / fetch a marketplace source | application/ |
| The concrete adapter behind one of the six ports | infrastructure/ |
How
- This context is a leaf by construction: it must never gain an edge to
tools,translate, orframework—tests/architecture/context-graph.arch.test.tsenforces the chain (framework → distribution, plus everything tokernel) and fails the build the moment a new edge appears. If a change seems to need one, the orchestration belongs to the caller (framework), not here — seeBASELINEintests/architecture/helpers.tsfor the one documented exception,distribution->framework, and the comment there that explains it (marketplace add --overwriteremoving before adding), which is framework work that has not yet been moved out. - A port here follows the port/adapter rule in
.claude/rules/00-architecture/: interface only, ≤5 methods, nonullin the return type unless "not found" is genuinely a normal domain state (documented per-port, not assumed). - An adapter owns every technical constant for its integration (API base URLs, cache TTLs,
error-pattern regexes for classifying a third-party failure) — none of that belongs in a port,
a use-case, or a domain model.
try/catchinside an adapter exists only to translate a raw error into a typed one fromkernel/errors.ts. - A new foreign catalog shape gets its own parser in
domain/catalog-parsers/, producing the samePluginCatalog/PluginCatalogEntryshape the Claude parser produces — callers above this context never branch on which format a catalog came from. - Follow the use-case rule in
.claude/rules/00-architecture/for the application layer's shape.
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.
- 4d ago First seen · 70 lines · 104 tokens per session scan A 3de2f0ddb555
distribution is a skill published in the GitHub repository ai-driven-dev/framework (464 stars, last pushed 2d ago), licensed MIT. It adds 104 tokens to every session and 988 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 2026-09-09.
Other skills, from other repositories
image-generation
Use this skill when the user requests to generate, create, imagine, or visualize images including characters, scenes, products, or any visual content. Supports structured prompts and reference images for guided generation.
podcast-generation
Use this skill when the user requests to generate, create, or produce podcasts from text content. Converts written content into a two-host conversational podcast audio format with natural dialogue.
vercel-deploy
Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as "Deploy my app", "Deploy this to production", "Create a preview deployment", "Deploy and give me the link", or "Push this live". No authentication required - returns preview URL and claimable deployment link.
skill-reviewer
Reviews DeerFlow skill packages for readiness, triggers, safety boundaries, resources, and evidence. Invoke when users ask to audit, grade, or production-check an existing skill.
build-monetized-app
Use when the task is building a new app on Eliza Cloud that earns money — chat apps, agent apps, MCP-backed tools, anything that calls the cloud's chat/messages/inference endpoints on behalf of users. Covers app registration, container deploy, markup configuration, affiliate header, app charge requests, x402 payment…
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes, capturing pane output, and managing terminal multiplexer windows. Enables parallel coding-agent orchestration, background process management, and REPL interaction via sockets. Use when the agent needs to launch, monitor, or coordinate…