What is proofloop-sol-luna?

A coding workflow for implementing a bounded change with temporary tests, a Git-based check before those tests become permanent, and an optional read-only review by Luna. TDD means writing tests as part of development; this workflow instead controls when agent-generated tests are admitted to the project.

Planning and implementing a focused change, running the test-distillation gate, integrating the patch, and optionally obtaining a fresh read-only review.

It separates building from deciding which generated tests should stay, while requiring project rules, scope, validation, and evidence to be checked.

proofloop-sol-luna — Skill by regenrek

Install

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.

agentmods

npx agentmods add skills/regenrek/codex-proofloop/proofloop-sol-luna

Any agent

npx skills add regenrek/codex-proofloop --skill proofloop-sol-luna

Clone the repo

git clone --depth 1 https://github.com/regenrek/codex-proofloop

Made for: Claude Code, Codex.

Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 757 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00058	$0.00757
Opus 5	$0.00029	$0.00378
Sonnet 5	$0.00012	$0.00151
Haiku 4.5	$0.00006	$0.00076

Measured 2d ago against content hash 44ce0589bc7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

proofloop-sol-luna 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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/test_distillation_gate.py, scripts/validate_config.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/proofloop-sol-luna/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Proofloop: Sol and Luna

Keep Sol responsible for intake, architecture, the sole-writer patch, integration, and the final decision. Luna is optional and read-only. This variant runs directly in Codex and does not require an orchestrator, pane manager, watcher, daemon, or long-lived heartbeat.

Start from project policy

Find the repository root and read every applicable AGENTS.md.
Locate the project profile named there. If none exists, adapt assets/project-profile.template.json and the AGENTS.md template inside the project.
Create one run contract from assets/run-contract.template.json. Keep paths project-relative and use one literal focused validation command.

Validate both documents:

python3 scripts/validate_config.py path/to/project-profile.json path/to/run-contract.json

Stop if policy, scope, ownership, or the source task is ambiguous. Never inspect credential contents or copy credentials into prompts, logs, contracts, or evidence.

Run the loop

Validate the profile and run contract.
Before the first edit, run python3 scripts/test_distillation_gate.py snapshot with absolute project, profile, and contract paths.
Execute BUILD or HARDEN exactly as the contract declares.
Run the literal focused validation command.
Run test_distillation_gate.py settle with the same three paths.
If luna_mode selects bounded-verifier, start one fresh read-only Luna review only after the candidate is frozen. If the host cannot provide that capability, stop and report it; never fake the review or replace it with a background watcher.
Let Sol integrate the result and return one evidence-backed handoff.

The test lifecycle is BUILD -> ACCEPT -> HARDEN -> DISTILL -> PROMOTE OR DROP. Do not add tracked tests while implementation is still changing. Temporary probes belong only in the declared ephemeral directory and must be removed before settlement. Acceptance starts a new HARDEN contract and a new baseline; never switch phases inside one contract.

Read the full file on GitHub · 65 lines

Files

What ships with it

9 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.

Changes

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 · 65 lines · 58 tokens per session scan A 44ce0589bc7b

Subscribe to this mod's changes

proofloop-sol-luna is a skill published in the GitHub repository regenrek/codex-proofloop (38 stars, last pushed 21d ago), licensed MIT. It adds 58 tokens to every session and 757 once invoked, about $0.0003 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 2026-08-30.

Git and workflow TDD Testing ai-agents codex developer-tools

agent-integration

Run all three agent integration phases sequentially: research, write-tests, and implement using E2E-first TDD (unit tests written last). For individual phases, use /agent-integration:research, /agent-integration:write-tests, or /agent-integration:implement. Use when the user says "integrate agent", "add agent…

entireio/cli · 89 tokens

engram-testing-coverage

TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.

Gentleman-Programming/engram · 25 tokens

test-generation

Use when the user asks for tests, mentions TDD, or when new code has been written and needs test coverage.

darrenhinde/OpenAgentsControl · 27 tokens

code-assist

Guides implementation of code tasks using test-driven development in an Explore, Plan, Code, Commit workflow. Acts as a Technical Implementation Partner and TDD Coach — following existing patterns, avoiding over-engineering, and producing idiomatic, modern code.

mikeyobrien/ralph-orchestrator · 53 tokens

tdd

Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

GreyDGL/PentestGPT · 33 tokens

css-design-tdd

Test-driven CSS design system modifications. Run checks before/after CSS changes to verify token usage, variable definitions, fallbacks, and consistency. Use when modifying CSS tokens, fixing design inconsistencies, or auditing CSS architecture.

xiaolai/vmark · 49 tokens