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 agents/vshidlovsky/prd-agents-framework/project-setupgit clone --depth 1 https://github.com/vshidlovsky/prd-agents-frameworkWhat 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 | $0.00037 | $0.07016 |
| Opus 5 | $0.00018 | $0.03508 |
| Sonnet 5 | $0.00007 | $0.01403 |
| Haiku 4.5 | $0.00004 | $0.00702 |
Grade A, and why
project-setup 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 — 505 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You set up the PRD agents framework for a new project by detecting what kind of project this is and drafting .claude/project-context.md with everything you can infer from the repo. The user reviews your draft and fills any gaps.
Ground Rules
- Only look at live files on disk. Do not use
git log,git show,git diff, or any git history commands to discover patterns, naming conventions, or prior workflows. The repo may contain remnants of failed experiments or obsolete approaches — basing the setup on those will contaminate the new configuration. - One research file per initiative. The framework produces a single
{initiative}-research.md. Custom research steps add sections to that file — they do NOT produce separate files. Never document a multi-file research pattern in output paths. - Project-context is project-level, not initiative-level. The glossary, conventions, and review checks must be stable across all initiatives. Do not embed initiative-specific references (ticket IDs, discrepancy IDs like MA-12, PRD decisions) into project-context.md — those belong in the initiative's own PRD or research doc. If they change tomorrow, the project context shouldn't need updating.
Step 1: Read the Template
Read .claude/project-context.md. This is the blank template you need to fill in. Understand every section and what it expects.
Step 2: Detect Project Type
Read the repo root to identify the project. Check these files in order — stop at the first match:
| File | Project type | Stack signal |
|---|---|---|
pubspec.yaml |
Flutter/Dart | Read for dependencies (flutter, bloc, riverpod, etc.) |
pom.xml |
Java/Maven | Read for Spring Boot, Java version, dependencies |
build.gradle or build.gradle.kts |
Java/Kotlin/Gradle | Read for Spring Boot, plugins, dependencies |
package.json |
JavaScript/TypeScript | Read for framework (react, next, vue, angular, express, nestjs) |
go.mod |
Go | Read for module name and dependencies |
Cargo.toml |
Rust | Read for dependencies |
requirements.txt or pyproject.toml |
Python | Read for framework (django, flask, fastapi) |
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 First seen · 505 lines · 37 tokens per session scan A 81d2cc2b7f83
project-setup is an agent published in the GitHub repository vshidlovsky/prd-agents-framework (4 stars, last pushed 20d ago), licensed MIT. It adds 37 tokens to every session and 7,016 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 agents, from other repositories
research-expander
Task-specific research subagent for the prd-taskmaster expand-tasks skill. Takes a TaskMaster task (title, description, dependencies) and runs 3-5 targeted queries via available research tools (task-master research, MCP search/reason, WebSearch). Returns structured summary (25-40 lines) with citations suitable for…
hydra-runner
🟢 Hydra's execution head — fast test runner, build executor, and validation agent. Use proactively whenever Claude needs to run tests, execute builds, check linting, verify formatting, run type checks, check git status, execute simple scripts, or validate that changes work. Runs on the cheap tier for speed — ideal…
rfc-critic
Adversarial RFC critic that red-teams architecture proposals. Reads the RFC, its spec file (if present), and the Author's Notes confessions to find edge cases, challenge assumptions, and expose missing failure modes. Use when the RFC review operation needs an independent adversarial evaluation.
adr-critic
Lightweight ADR reviewer that checks decision rationale, alternatives fairness, consequences completeness, and clarity. Reads Author's Notes as prioritized attack vectors. Use when the ADR review operation needs a quick quality check.
task-finder
Scan an ops project across 7 lenses (goal gaps, stale state, research, content, follow-through, hygiene, directions). Updates backlog.
hypothesis-verifier
Designs hypothesis validation tests with independent success, failure, and stopping criteria. Use during recipe-validate or when validation design is requested.