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 richkuo/rk-skills --skill prd-to-issuesgit clone --depth 1 https://github.com/richkuo/rk-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/skills/richkuo/rk-skills/prd-to-issues)<a href="https://agentmods.dev/skills/richkuo/rk-skills/prd-to-issues"><img src="https://agentmods.dev/badge/skills/richkuo/rk-skills/prd-to-issues/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/richkuo/rk-skills/prd-to-issues"><img src="https://agentmods.dev/badge/skills/richkuo/rk-skills/prd-to-issues.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 | $0.00067 | $0.01613 |
| Opus 5 | $0.00034 | $0.00807 |
| Sonnet 5 | $0.00013 | $0.00323 |
| Haiku 4.5 | $0.00007 | $0.00161 |
Grade A, and why
prd-to-issues 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 2d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
prd-to-issues
Produce a complete, dependency-ordered backlog an agent can implement from each issue plus its cited PRD. The deliverable ends at verified GitHub issues; building and dispatch need their own instruction.
Follow the target repo's CLAUDE.md/AGENTS.md Response Style and attribution rules. Read github-issue-format before composing bodies. Read validate-issue step 6 and its complexity-scoring reference for scoring and routing; they own the formula and band tables. Do not start the validation workflow.
1. Establish the source and existing work
- Identify the target repo, PRD revision, and release scope. Read the full PRD, repo instructions, code, and tests; separate implemented from planned work. In an empty repo, mark proposed boundaries as proposed.
- Fetch all open and closed issues and milestones, with pagination. Reuse an issue only after comparing body, acceptance criteria, and implementation evidence; a matching title or closed state proves nothing. Preserve existing work and deliberate execution overrides.
- Cite a stable PRD link with its verified section heading; prefer a commit-pinned source. A local or uncommitted source gets a durable, accessible home before filing. Never invent section numbers or publish source material outside the authorized destination.
- Resolve an ambiguous repo or conflicting source revision before any write.
2. Map requirements and dependencies
Hold the requirement-to-issue map, draft bodies, dependency graph, and each issue's create/reuse/update action while you work.
- Map every in-scope requirement to a draft key, an existing issue, or verified implementation. Record exclusions and deferrals with reasons. Give each shared invariant an owning issue and name the consumers that enforce it.
- Size each issue as one coherent result, implementable and verifiable in one pull request (PR) after its prerequisites. No fixed issue count or milestone size. Keep inseparable changes together; split large candidates by
validate-issuestep 7. - Derive milestones from prerequisite order plus a verifiable completion outcome. Reuse suitable milestones and the user's release names; never pull deferred roadmap features into the requested release.
- Depends on: the successor needs the predecessor's code or product result. Runs after: ordering only, such as independent edits to one package that must not overlap; name the actual conflict, since a shared location alone is not enough.
- Reject missing references, self-references, duplicate edges, a predecessor in both fields, and cycles across the combined graph, recursing into referenced existing issues outside the milestone. Milestone order must let every prerequisite finish first; membership alone is no edge. Mark serial prerequisites, concurrent work, and safety-critical issues.
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.
- 2d ago Changed · -22 lines · -30 tokens per session d4e9a3f2d46d
- 4d ago Changed · -7 lines 94c2904cfa0a
- 5d ago Changed 5ad3c259e703
- 7d ago Changed · +4 lines 02e260b16008
- 11d ago First seen · 92 lines · 97 tokens per session scan A 5fd202e8a72d
prd-to-issues is a skill published in the GitHub repository richkuo/rk-skills (49 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 1,613 once invoked, about $0.0003 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 skills, from other repositories
to-issues
A planning aid that breaks a PRD or technical specification into small implementation issues, each covering a complete, demonstrable piece of work.
issue-fields-migration
Bulk-migrate metadata to GitHub issue fields from two sources: repo labels (e.g. priority labels to a Priority field) and Project V2 fields. Use when users say "migrate my labels to issue fields", "migrate project fields to issue fields", "convert labels to issue fields", "copy project field values to issue fields"…
flowstudio-power-automate-governance
Govern Power Automate flows and Power Apps at scale using the FlowStudio MCP cached store. Classify flows by business impact, detect orphaned resources, audit connector usage, enforce compliance standards, manage notification rules, and compute governance scores — all without Dataverse or the CoE Starter Kit. Load…
gtm-enterprise-account-planning
Strategic account planning and execution for enterprise deals. Use when planning complex sales cycles, managing multiple stakeholders, applying MEDDICC qualification, tracking deal health, or building mutual action plans. Includes the "stale MAP equals dead deal" pattern.
gtm-enterprise-onboarding
Four-phase framework for onboarding enterprise customers from contract to value realization. Use when implementing new enterprise customers, preventing churn during onboarding, or solving the adoption cliff that kills deals post-go-live. Includes the Week 4 ghosting pattern.
gtm-operating-cadence
Design meeting rhythms, metric reporting, quarterly planning, and decision-making velocity for scaling companies. Use when decisions are slow, planning is broken, the company is growing but alignment is worse, or leadership meetings consume all time without producing decisions.