Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/siarhei-belavus/agent-publicnpx agentmods add skills/siarhei-belavus/agent-public/prd-to-planWrote 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/siarhei-belavus/agent-public/prd-to-plan)<a href="https://agentmods.dev/skills/siarhei-belavus/agent-public/prd-to-plan"><img src="https://agentmods.dev/badge/skills/siarhei-belavus/agent-public/prd-to-plan/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/siarhei-belavus/agent-public/prd-to-plan"><img src="https://agentmods.dev/badge/skills/siarhei-belavus/agent-public/prd-to-plan.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 | $0.00032 | $0.00573 |
| Opus 5 | $0.00016 | $0.00287 |
| Sonnet 5 | $0.00006 | $0.00115 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
prd-to-plan 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.
What it actually says
Your job is to convert a PRD into a practical implementation plan that another agent can execute safely.
The plan should be sequenced, reviewable, and biased toward visible progress. Prefer vertical slices that validate assumptions early over large horizontal phases.
Process
- Read and understand the PRD
Extract the key information:
- user problem and desired outcomes
- critical workflows
- constraints and non-goals
- major risks and open questions
If the PRD path is not given explicitly, infer the PRD slug from the provided PRD artifact and use that slug consistently.
- Derive an implementation strategy
Create a strategy that:
- validates risky assumptions early
- delivers value incrementally
- keeps the system working after each phase
- limits branching complexity and migration risk
- makes validation straightforward at each step
Avoid plans that defer all user-visible value until the end.
- Create the plan file
Write the plan to:
.prd/<prd-slug>/plans/implementation-plan.md
Create the plans/ directory if it does not exist.
- Write the plan
Use this structure:
# Implementation Plan: <initiative name>
## Parent PRD
.prd/<prd-slug>/prd.md
## Planning Principles
- Principle 1
- Principle 2
## Phase 1: <name>
### Goal
What this phase proves or delivers.
### Scope
- Step 1
- Step 2
### Validation
- Test or check 1
- Test or check 2
### Risks / Notes
- Important warning or dependency
## Phase 2: <name>
...
## Dependencies and Order
- Cross-phase dependency 1
- Cross-phase dependency 2
## Open Questions
- Question 1
- Question 2
Each phase should be small enough to review and validate, but large enough to produce meaningful progress.
5. Make the plan executable
The plan should be detailed enough that another agent can pick it up in a fresh context window without extra explanation.
That means:
- explicit phase goals
- clear sequencing
- concrete validation steps
- important constraints called out near the relevant work
- no reliance on unstated tribal knowledge
6. Final response
In your final response:
- summarize the implementation strategy
- provide the final plan path
- mention any major unresolved risks or questions
## Communication
Honor active caveman mode for user-facing replies per `../../references/communication-mode.md`. Keep durable artifacts normal unless the human asks otherwise. Drop caveman for safety/clarity when needed, then resume.
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 · 104 lines · 32 tokens per session scan A 28a6dfbb0e15
prd-to-plan is a skill published in the GitHub repository siarhei-belavus/agent-public (2 stars, last pushed 3mo ago), licensed MIT. It adds 32 tokens to every session and 573 once invoked, about $0.0002 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 2026-08-31.
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…