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/bestagentkits/agency-skillsnpx agentmods add skills/bestagentkits/agency-skills/code-to-prdWrote 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/bestagentkits/agency-skills/code-to-prd)<a href="https://agentmods.dev/skills/bestagentkits/agency-skills/code-to-prd"><img src="https://agentmods.dev/badge/skills/bestagentkits/agency-skills/code-to-prd/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/bestagentkits/agency-skills/code-to-prd"><img src="https://agentmods.dev/badge/skills/bestagentkits/agency-skills/code-to-prd.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 | $0.00151 | $0.04508 |
| Opus 5.5 | $0.00060 | $0.01803 |
| Sonnet 5.5 | $0.00030 | $0.00902 |
| Haiku 4.5 | $0.00015 | $0.00451 |
Grade A, and why
code-to-prd 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 — 497 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Name
Code → PRD
Description
Reverse-engineer any frontend, backend, or fullstack codebase into a complete Product Requirements Document (PRD). Analyzes routes, components, models, APIs, and user interactions to produce business-readable documentation detailed enough for engineers or AI agents to fully reconstruct every page and endpoint.
Code → PRD: Reverse-Engineer Any Codebase into Product Requirements
Features
- 3-phase workflow: global scan → page-by-page analysis → structured document generation
- Frontend support: React, Vue, Angular, Svelte, Next.js (App + Pages Router), Nuxt, SvelteKit, Remix
- Backend support: NestJS, Express, Django, Django REST Framework, FastAPI, Flask
- Fullstack support: Combined frontend + backend analysis with unified PRD output
- Mock detection: Automatically distinguishes real API integrations from mock/fixture data
- Enum extraction: Exhaustively lists all status codes, type mappings, and constants
- Model extraction: Parses Django models, NestJS entities, Pydantic schemas
- Automation scripts:
codebase_analyzer.pyfor scanning,prd_scaffolder.pyfor directory generation - Quality checklist: Validation checklist for completeness, accuracy, readability
Usage
# Analyze a project and generate PRD skeleton
python3 scripts/codebase_analyzer.py /path/to/project -o analysis.json
python3 scripts/prd_scaffolder.py analysis.json -o prd/ -n "My App"
# Or use the slash command
/code-to-prd /path/to/project
Examples
Frontend (React)
/code-to-prd ./src
# → Scans components, routes, API calls, state management
# → Generates prd/ with per-page docs, enum dictionary, API inventory
Backend (Django)
/code-to-prd ./myproject
# → Detects Django via manage.py, scans urls.py, views.py, models.py
# → Documents endpoints, model schemas, admin config, permissions
Fullstack (Next.js)
/code-to-prd .
# → Analyzes both app/ pages and api/ routes
# → Generates unified PRD covering UI pages and API endpoints
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 189 B
- assets/sample-analysis.json 2.9 KB
- expected_outputs/sample-enum-dictionary.md 729 B
- expected_outputs/sample-page-user-list.md 3.0 KB
- expected_outputs/sample-prd-readme.md 1.7 KB
- references/framework-patterns.md 7.6 KB
- references/prd-quality-checklist.md 2.9 KB
- scripts/.gitignore 5 B
- scripts/codebase_analyzer.py 26 KB runs code
- scripts/prd_scaffolder.py 15 KB runs code
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 · 497 lines · 151 tokens per session scan A 7a11ba564076
code-to-prd is a skill published in the GitHub repository bestagentkits/agency-skills (24 stars, last pushed 4mo ago), licensed MIT. It adds 151 tokens to every session and 4,508 once invoked, about $0.0006 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
reproduce-and-fix-issues
Reproduce triaged Slack bugs through a configured app-control adapter, verify existing fixes, and open a bounded draft pull request only after before-and-after proof. Use only from the configured Benny repro automation.
setup-pstack
Configure which models pstack uses per role and at what reasoning budget. Detects your available models and writes an always-applied rule that overrides the skill defaults. Use for /setup-pstack, "configure pstack models", "pstack budget", or changing pstack's model choices.
exposure-risk-quantification
FAIR-aligned exposure quantification: turns a pile of recon findings into a defensible 0-100 + A-F org risk score (Likelihood x Impact, three ownership-aware factors: exposure/threat/impact), an ownership + proof demotion cap so unproven or weakly-owned findings can't inflate the number, a $-denominated FAIR…
no-comments
Spawn Comment Sicko, fix accepted findings, and offer encodings for claimed constraints.
design-audit
Premium UI/UX design audit and refinement skill. Conducts systematic visual audits of existing apps and produces phased, implementation-ready design plans. Use this skill whenever the user asks to audit a UI, improve an app's visual design, make an interface feel more polished or premium, review design consistency…
bencium-code-conventions
Bence's code style, tech stack, and workflow conventions.