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 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/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/lerianstudio/ring/planning-large-features"><img src="https://agentmods.dev/badge/skills/lerianstudio/ring/planning-large-features.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00089 | $0.01556 |
| Opus 5.5 | $0.00036 | $0.00622 |
| Sonnet 5.5 | $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 1mo 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 — 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.
- 1mo ago 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 (218 stars, last pushed 6d ago), licensed Apache-2.0. It adds 89 tokens to every session and 1,556 once invoked, about $0.0004 per session on Opus 5.5. 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
retro
Engineering retrospective from git metrics. Reports deployment frequency, release cycle span, churn hotspots, backlog health. Outputs narrative report with 3+ actionable items. Flags: --since, --path, explicit range argument.
backlog
Manage the project's tech debt backlog. Add, list, fix, wontfix, delete, prioritize, and suggest batch actions on tracked issues, run by the user to manage accumulated debt (skills file their findings through /.zuvo/backlog-add themselves, never through this skill). Modes: list [category], add [description], fix B- …
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
publish-artifacts-to-r3
Publish HTML pages, documents, files, or code changes to r3 for human review, and respond to feedback on existing r3 artifacts. Use when the user asks to use r3 or supplies an r3 artifact or feedback command.
revert
Git-aware revert that understands Draft tracks, phases, and tasks. Safely undo work at task, phase, or track level. Use when the user asks to 'revert this track', 'undo a phase', 'revert task X', or says 'roll back the last task', 'undo this work'.