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.
git clone --depth 1 https://github.com/bvdr/claude-pluginsWrote 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/bvdr/claude-plugins/proof-driven-development)<a href="https://agentmods.dev/commands/bvdr/claude-plugins/proof-driven-development"><img src="https://agentmods.dev/badge/commands/bvdr/claude-plugins/proof-driven-development/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/bvdr/claude-plugins/proof-driven-development"><img src="https://agentmods.dev/badge/commands/bvdr/claude-plugins/proof-driven-development.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 | $0.00110 | $0.01387 |
| Opus 5.5 | $0.00044 | $0.00555 |
| Sonnet 5.5 | $0.00022 | $0.00277 |
| Haiku 4.5 | $0.00011 | $0.00139 |
Grade A, and why
proof-driven-development scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
query the DB, curl the endpoint. Diagnosis-by-evidence converges; diagnosis-by-guessing oscillates. How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Proof-Driven Development
A repeatable shape for turning a vague, high-blast-radius request into shipped, proven work. Core stance: never assert without evidence, never decide without the user, never claim done without proof.
When to use (calibrate first)
Trigger = ambiguity × blast-radius. Run the full weight only when the ask is underspecified AND touches auth, identity, money, data integrity, or multiple systems. For a localized, well-specified change, skip to Phase 6 (change + verify). Don't ceremony-tax a typo fix.
Announce the shape, then work the phases in order.
Phase 1 — Ground in reality
Read the actual code, ticket, and prior memory before theorizing. Dispatch parallel Explore
agents for breadth. Pull the ticket/source of truth directly (API, not assumptions). Output a
short assessment that states the central challenge and the blast radius — not a feature summary.
Phase 2 — Proof-tagged assumptions (the highest-leverage step)
Post assumptions split into task-related / logic / codebase, as a table:
# | assumption | TRUE / TBD | note (proof or default)
- Tag each
TRUEonly with proof: afile:line, a query result, or a ticket fact. - Tag genuine product choices
TBDwith a recommended default in the note. - Resolve the
TBDrows with the user viaAskUserQuestion— verify facts yourself, escalate only decisions. This isolates the few real choices from the many things you can just check.
Phase 3 — Lock a testable GOAL
Convert the confirmed assumptions into a definition of done = pass/fail criteria, each paired with how it will be PROVEN (which automated test, live check, or artifact). Number them. Get explicit sign-off ("lock the goal"). Treat later scope additions as new goals, not edits to the locked one.
Phase 4 — Plan as TDD
Write an implementation plan of bite-sized tasks with real code, no placeholders (use
superpowers:writing-plans if available). Each task: failing test → minimal code → green →
commit. Map every goal criterion to a task before starting.
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 · 109 lines · 110 tokens per session scan A 459553188435
proof-driven-development is a command published in the GitHub repository bvdr/claude-plugins (4 stars, last pushed 4mo ago), licensed MIT. It adds 110 tokens to every session and 1,387 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
eval-scaffold
Scaffold a real eval suite for an app's prompts/agents so a change can be proven better, not eyeballed.
bug
Reproduce then TDD-fix a ready-for-agent bug ticket in this checkout. Web bugs get a browser repro first.
build
Implement the next ready task from .forge/tasks.yaml using TDD discipline.
uw-cmd-implement-feature
Build a feature complete: interrogation -> TDD implementation -> game feel -> documentation — all in one pass.
uw-cmd-create
Generate isolated code following a test-driven development approach.
bugfix
Bug fix workflow: root cause analysis → user review → regression test + fix via TDD.