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 d-padmanabhan/agent-engineering-handbook --skill skills-compositiongit clone --depth 1 https://github.com/d-padmanabhan/agent-engineering-handbookWrote 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/d-padmanabhan/agent-engineering-handbook/skills-composition)<a href="https://agentmods.dev/skills/d-padmanabhan/agent-engineering-handbook/skills-composition"><img src="https://agentmods.dev/badge/skills/d-padmanabhan/agent-engineering-handbook/skills-composition/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/d-padmanabhan/agent-engineering-handbook/skills-composition"><img src="https://agentmods.dev/badge/skills/d-padmanabhan/agent-engineering-handbook/skills-composition.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 54 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00095 | $0.03039 |
| Opus 5 | $0.00048 | $0.01520 |
| Sonnet 5 | $0.00019 | $0.00608 |
| Haiku 4.5 | $0.00010 | $0.00304 |
Grade A, and why
skills-composition 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 — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skills Composition - Patterns
How to build workflows that span more than one Cursor / Agent Skill cleanly. Covers chaining, scope resolution, graceful degradation, and the discipline of "one skill, one capability".
Companion rules:
015-context-engineering.mdc- prompt packing, retrieval, compaction100-core.mdc- SOLID / DRY / KISS / YAGNI
When to invoke
Use when designing:
- A slash command that needs to call more than one skill in sequence
- A skill that calls helpers in another skill (vs duplicating the logic)
- A workflow where a downstream skill is optional (graceful degradation)
- A new skill where the right answer might be "extend an existing skill instead"
Do not use for:
- Single-skill workflows - just call the skill directly
- One-off scripts - skills are for repeatable workflows
The Five Golden Rules
- One skill, one capability. A skill answers one question well. Multiple capabilities = multiple skills.
- Compose via commands, not by importing. Skills do not "import" each other; a slash command (or another skill's workflow) orchestrates them.
- Project scope wins over personal scope. A project-scope skill (
.cursor/skills/) wins over a personal-scope copy (~/.cursor/skills/) of the same name. - Auto-detect siblings; degrade gracefully. When skill A optionally extends skill B, A checks for B at known paths and skips silently if absent.
- HITL gates between phases for irreversible steps. Even within a single command, prompt before destructive or expensive steps.
Skill scope resolution
Cursor (and Claude Code) discover skills at multiple paths. The resolution order:
flowchart LR
invoke[Skill / command invocation]
invoke --> proj{".cursor/skills/<name>/SKILL.md exists?"}
proj -->|"Yes"| use1["Use project-scope skill"]
proj -->|"No"| user{"~/.cursor/skills/<name>/SKILL.md exists?"}
user -->|"Yes"| use2["Use personal-scope skill"]
user -->|"No"| compat{".claude/skills or .codex/skills exists?"}
compat -->|"Yes"| use3["Use compatibility-scope skill"]
compat -->|"No"| missing[Skill not found]
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 · 281 lines · 95 tokens per session scan A 437abbd0010d
skills-composition is a skill published in the GitHub repository d-padmanabhan/agent-engineering-handbook (17 stars, last pushed today), licensed MIT. It adds 95 tokens to every session and 3,039 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…