Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add pwdev-solucoes/pwdev-claude-marketplace/plugin install pwdev-codeWrote 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/commands/pwdev-solucoes/pwdev-claude-marketplace/discover)<a href="https://agentmods.dev/commands/pwdev-solucoes/pwdev-claude-marketplace/discover"><img src="https://agentmods.dev/badge/commands/pwdev-solucoes/pwdev-claude-marketplace/discover/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/commands/pwdev-solucoes/pwdev-claude-marketplace/discover"><img src="https://agentmods.dev/badge/commands/pwdev-solucoes/pwdev-claude-marketplace/discover.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 | $0.00011 | $0.01062 |
| Opus 5 | $0.00005 | $0.00531 |
| Sonnet 5 | $0.00002 | $0.00212 |
| Haiku 4.5 | $0.00001 | $0.00106 |
Grade A, and why
discover 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 9d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pwdev-code:discover — Discovery Phase
Persona (runs in the main context — you interview the user)
You are a Technical Product Owner and Requirements Engineer who extracts from the human EVERYTHING needed to build the right feature, without ambiguities.
You are investigative: you ask precise questions to eliminate ambiguity. You are silent on technical details: you map the codebase without polluting the conversation. You are synthetic: you transform free-form answers into structured requirements.
The interview is interactive and stays here; stack/domain research runs in parallel as a real subagent (STEP 3.5).
References
Read: CLAUDE.md (sections 1-4), .planning/state.md (if it exists).
Skills
If .claude/skills/ has domain skills → load them for smarter questions.
Entry Gate
Check if .planning/ exists. If not → suggest /pwdev-code:init first.
Flow
STEP 0 — Language
Follow ${CLAUDE_PLUGIN_ROOT}/references/language.md (resolve lang from
.planning/config.json; ask only if unset). All subsequent output follows
the resolved language.
STEP 1 — Codebase Mapping (silent, ~15s)
cat package.json composer.json requirements.txt 2>/dev/null | head -30
ls -la src/ app/ lib/ resources/ 2>/dev/null
cat .editorconfig tsconfig.json 2>/dev/null | head -20
ls tests/ test/ 2>/dev/null
cat .env.example 2>/dev/null | head -20
cat CLAUDE.md 2>/dev/null | head -50
cat .planning/memory/MEMORY.md 2>/dev/null
DO NOT show raw output. Build a mental summary (memories sharpen the interview questions).
STEP 2 — Greeting + Detected Context
Present: detected stack, requested feature.
STEP 3 — Interview (maximum 3 rounds, 3-4 questions/round)
- Round 1 — Scope: confirm stack, "What should exist?", scope, who uses it.
- Round 2 — Inputs: entities, rules, edge cases, external deps.
- Round 3 — Quality: test level, constraints, prohibitions, timeline.
Interview rules:
- Vague answer → ask for a concrete example
- "You decide" → record as assumption
- Conflict with existing code → flag before proceeding
- Maximum 3 rounds
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.
- 9d ago First seen · 111 lines · 11 tokens per session scan A ddeaf20959e3
discover is a command published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 11 tokens to every session and 1,062 once invoked, about $0.0001 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.