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 agentmods add skills/lerianstudio/ring/planning-large-featuresnpx skills add LerianStudio/ring --skill planning-large-featuresgit clone --depth 1 https://github.com/LerianStudio/ringWrote 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/lerianstudio/ring/planning-large-features)<a href="https://agentmods.dev/skills/lerianstudio/ring/planning-large-features"><img src="https://agentmods.dev/badge/skills/lerianstudio/ring/planning-large-features.svg" alt="Measured on agentmods" 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 | $0.00089 | $0.01556 |
| Opus 5 | $0.00044 | $0.00778 |
| Sonnet 5 | $0.00018 | $0.00311 |
| Haiku 4.5 | $0.00009 | $0.00156 |
Grade A, and why
ring:planning-large-features 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 yesterday.
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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Large Track Pre-Dev Workflow (8 Gates)
When to use
- Feature takes >=2 days to implement
- Adds new external dependencies (APIs, databases, libraries)
- Creates new data models or entities
- Requires multi-service integration
- Uses new architecture patterns
- Requires team collaboration
Skip when
- Feature is simple (<2 days, existing patterns) - use ring:planning-small-features instead
- No new dependencies, data models, or architecture patterns needed
Sequence
Runs before: ring:running-dev-cycle, ring:executing-plans
Related
Complementary: ring:planning-small-features, ring:creating-worktrees, ring:product-designer + ring:validating-ux-completeness (standalone UX step, recommended when feature has UI) Skills orchestrated:
- ring:researching-features
- ring:writing-prds
- ring:mapping-feature-relationships
- ring:writing-trds
- ring:designing-api-contracts
- ring:designing-data-model
- ring:pinning-dependency-versions
- ring:writing-plans
Running the Large Track pre-development workflow for features that take ≥2 days, add new external dependencies, create new data models, require multi-service integration, use new architecture patterns, or require team collaboration.
For simple features (<2 days, existing patterns), use ring:planning-small-features instead.
Gate Map
| Gate | Skill | Output |
|---|---|---|
| 0 | ring:researching-features | research.md |
| 1 | ring:writing-prds | prd.md |
| 2 | ring:mapping-feature-relationships | feature-map.md |
| 3 | ring:writing-trds | trd.md |
| 4 | ring:designing-api-contracts | openapi.yaml |
| 5 | ring:designing-data-model | schema.sql / schema.prisma (stack-native) |
| 6 | ring:pinning-dependency-versions | dependencies.md |
| 7 | ring:writing-plans | plan.md |
All artifacts saved to: docs/pre-dev/<feature-name>/
Step 1: Gather Feature Name
AskUserQuestion: "What is the name of your feature?" (kebab-case, e.g., "auth-system", "payment-processing")
Step 2: Topology Discovery (MANDATORY)
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.
- yesterday First seen · 119 lines · 89 tokens per session scan A 1e51b646bf66
ring:planning-large-features is a skill published in the GitHub repository LerianStudio/ring (210 stars, last pushed 16d ago), licensed Apache-2.0. It adds 89 tokens to every session and 1,556 once invoked, about $0.0004 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
feature
Full per-feature pipeline: implement → testloop → evaluator challenge → coder feedback → document → commit.
stories
Story Generator - PRD to Implementation Stories.
status
/status - Project Status Dashboard.
workflow
You are the Workflow Orchestrator: a strategic routing engine that analyzes the user's current task and context, then designs and guides the optimal sequence of SkillFoundry commands to accomplish their goal efficiently. You do not write code — you design execution paths.
orchestrate
Use this agent when you need rigorous project management following the NASAB framework principles.
tech-lead
Use this agent for technical decision arbitration, cross-team coordination, technical mentorship, and strategic technical planning.