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 dinglebear-ai/dendrite --skill compose-skillgit clone --depth 1 https://github.com/dinglebear-ai/dendriteWrote 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/dinglebear-ai/dendrite/compose-skill)<a href="https://agentmods.dev/skills/dinglebear-ai/dendrite/compose-skill"><img src="https://agentmods.dev/badge/skills/dinglebear-ai/dendrite/compose-skill/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/dinglebear-ai/dendrite/compose-skill"><img src="https://agentmods.dev/badge/skills/dinglebear-ai/dendrite/compose-skill.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 | $0.00069 | $0.03881 |
| Opus 5.5 | $0.00028 | $0.01552 |
| Sonnet 5.5 | $0.00014 | $0.00776 |
| Haiku 4.5 | $0.00007 | $0.00388 |
Grade A, and why
compose-skill 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 2mo 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.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
What ships with it
45 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.
- agents/openai.yaml 428 B
- assets/compose-multiplatform-icon.svg 1015 B
- LICENSE 1.0 KB
- README.md 24 KB
- references/accessibility.md 6.8 KB
- references/animations-advanced.md 7.5 KB
- references/animations.md 7.7 KB
- references/anti-patterns.md 7.9 KB
- references/architecture.md 8.7 KB
- references/ci-cd-distribution.md 7.4 KB
- references/clean-code.md 8.2 KB
- references/compose-essentials.md 8.0 KB
- references/coroutines-flow-advanced.md 4.4 KB
- references/coroutines-flow.md 7.5 KB
- references/cross-platform.md 8.7 KB
- references/datastore.md 7.8 KB
- references/dependency-injection.md 4.0 KB
- references/gradle-build.md 8.2 KB
- references/hilt.md 8.8 KB
- references/image-loading.md 8.1 KB
- references/ios-swift-interop.md 8.0 KB
- references/koin.md 9.2 KB
- references/lists-grids.md 4.6 KB
- references/material-design.md 8.7 KB
- references/mvi.md 9.2 KB
- references/mvvm.md 7.9 KB
- references/navigation-2-di.md 4.6 KB
- references/navigation-2.md 8.3 KB
- references/navigation-3-di.md 5.1 KB
- references/navigation-3.md 8.3 KB
- references/navigation-migration.md 4.9 KB
- references/navigation.md 5.0 KB
- references/networking-ktor-architecture.md 9.2 KB
- references/networking-ktor-auth.md 7.0 KB
- references/networking-ktor-testing.md 5.6 KB
- references/networking-ktor.md 8.9 KB
- references/paging-mvi-testing.md 5.6 KB
- references/paging-offline.md 4.8 KB
- references/paging.md 9.1 KB
- references/performance.md 7.5 KB
- references/resources.md 9.1 KB
- references/room-database.md 10 KB
- references/testing.md 7.3 KB
- references/ui-ux.md 5.0 KB
- scripts/validate.sh 85 KB runs code
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.
- 2mo ago First seen · 205 lines · 69 tokens per session scan A 3c224dda5399
compose-skill is a skill published in the GitHub repository dinglebear-ai/dendrite (1 stars, last pushed 1mo ago), licensed AGPL-3.0. It adds 69 tokens to every session and 3,881 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.
compose-skill compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| compose-skilldinglebear-ai/dendrite | Skill | 1 | 1mo ago | AGPL-3.0 | A | 69 | Claude Code, Codex |
| vercel-react-native-skillsfcakyon/claude-codex-settings | Skill | 1.2k | yesterday | Apache-2.0 | A | 57 | Claude Code |
| sim-usecafe3310/public-agent-skills | Skill | 256 | yesterday | Apache-2.0 | A | 48 | Claude Code, Codex |
| lov-mobile-adaptlovstudio/skills | Skill | 72 | 3d ago | MIT | A | 63 | Claude Code |
| lov-app-releaselovstudio/skills | Skill | 72 | 3d ago | MIT | A | 64 | Claude Code |
| android-ui-engineeringGuillemRoca/agent-skills-android | Skill | 5 | 1mo ago | MIT | A | 52 | Claude Code |
| security-and-hardeningGuillemRoca/agent-skills-android | Skill | 5 | 1mo ago | MIT | A | 62 | Claude Code |