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.
git clone --depth 1 https://github.com/Owl-Listener/ai-design-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/commands/owl-listener/ai-design-skills/build-chain)<a href="https://agentmods.dev/commands/owl-listener/ai-design-skills/build-chain"><img src="https://agentmods.dev/badge/commands/owl-listener/ai-design-skills/build-chain/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/commands/owl-listener/ai-design-skills/build-chain"><img src="https://agentmods.dev/badge/commands/owl-listener/ai-design-skills/build-chain.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 | $0.00011 | $0.00463 |
| Opus 5 | $0.00005 | $0.00231 |
| Sonnet 5 | $0.00002 | $0.00093 |
| Haiku 4.5 | $0.00001 | $0.00046 |
Grade A, and why
build-chain 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 11d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are designing a prompt chain. Use only skills from the prompt-architecture plugin. Follow this process:
Step 1: Understand the Task
- What is the end goal?
- Why can't a single prompt accomplish this?
- What are the intermediate outputs needed?
Step 2: Design the Chain Structure
Using chain-of-thought-design:
- Choose the chain variant: linear, branching, iterative, or debate
- Define each step in the chain
- For each step, define the input (from user or previous step) and expected output
- Map dependencies between steps
Step 3: Design Each Step's Prompt
Using system-prompt-structure and constraint-specification:
- For each step, write the prompt
- Define constraints specific to that step
- Ensure each step's output format matches the next step's expected input
Step 4: Design Templates
Using template-design:
- Identify which parts of each prompt are fixed and which are variable
- Create templates for each step with clearly defined variables
- Define how outputs from one step feed into variables of the next
Step 5: Add Examples Per Step
Using few-shot-patterns:
- For each step, provide at least one example of expected input and output
- Ensure examples flow coherently across the chain
Step 6: Design Context Flow
Using context-engineering:
- Define what context carries forward between steps
- Specify what gets summarised or dropped between steps
- Allocate context budgets per step
- Design the overall information flow through the chain
Step 7: Design Failure Handling
- What happens if a step produces poor output?
- Define retry logic and quality gates between steps
- Design fallback paths for chain failures
Output
Deliver a complete prompt chain specification:
- Chain overview diagram showing all steps and connections
- Individual prompts for each step
- Templates with variable definitions
- Context flow specification
- Examples flowing through the full chain
- Failure handling and quality gates
- Estimated token budget per step and total
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.
- 11d ago First seen · 50 lines · 11 tokens per session scan A 95758acab295
build-chain is a command published in the GitHub repository Owl-Listener/ai-design-skills (172 stars, last pushed 3mo ago), licensed MIT. It adds 11 tokens to every session and 463 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.