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 skills/regenrek/codex-proofloop/proofloop-herdr-sol-luna-fablenpx skills add regenrek/codex-proofloop --skill proofloop-herdr-sol-luna-fablegit clone --depth 1 https://github.com/regenrek/codex-proofloopWrote 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/regenrek/codex-proofloop/proofloop-herdr-sol-luna-fable)<a href="https://agentmods.dev/skills/regenrek/codex-proofloop/proofloop-herdr-sol-luna-fable"><img src="https://agentmods.dev/badge/skills/regenrek/codex-proofloop/proofloop-herdr-sol-luna-fable.svg" alt="Measured on agentmods" 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 | $0.00109 | $0.01099 |
| Opus 5 | $0.00055 | $0.00549 |
| Sonnet 5 | $0.00022 | $0.00220 |
| Haiku 4.5 | $0.00011 | $0.00110 |
Grade A, and why
proofloop-herdr-sol-luna-fable 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 6d 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.
This is a copy
89% identical to proofloop-herdr-sol-luna-fable-planr — 9 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Proofloop Herdr: Sol, Luna, and Fable
Keep Sol responsible for the task, architecture, sole-writer implementation, integration, and final decision. Add another agent only when its distinct role materially improves the run.
Start from project policy
-
Discover the repository root with its version-control or project tooling; otherwise use the explicit working directory.
-
Read the applicable
AGENTS.mdfiles and locate the project profile they name. If none exists, adapt assets/project-profile.template.json and the AGENTS.md template inside the project before orchestrating. -
Create one run contract from assets/run-contract.template.json. Keep allowed paths project-relative and choose one literal 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.
Select the smallest useful topology
- Use Sol only for ordinary implementation and deterministic validation.
- Add one Luna Max silent sentinel only when the run contract explicitly selects it for a
long-running Sol implementation.
luna_mode: nullcreates no Luna pane or process. Start it only with scripts/silent_sentinel.py; the script refuses an unselected mode and exits at settlement, owner loss, mandatory stop, or its deadline. - Add one fresh Luna Max bounded verifier only when project policy selects it and independent verification is worth a separate session.
- Add one fresh Luna Max interactive operator only for sustained UI or manual interaction that cannot be represented by the validation command.
- Ask Fable once per hypothesis, either before implementation to challenge it or afterward for final semantic review. Do not use both by default.
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 243 B
- assets/AGENTS.md.template.md 3.2 KB
- assets/project-profile.template.json 2.7 KB
- assets/run-contract.template.json 2.3 KB
- assets/test-admission.template.json 927 B
- references/orchestration.md 9.9 KB
- references/testing.md 4.9 KB
- scripts/silent_sentinel.py 21 KB runs code
- scripts/test_distillation_gate.py 19 KB runs code
- scripts/validate_config.py 26 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.
- 6d ago First seen · 86 lines · 109 tokens per session scan A 73025d93004e
proofloop-herdr-sol-luna-fable is a skill published in the GitHub repository regenrek/codex-proofloop (38 stars, last pushed 25d ago), licensed MIT. It adds 109 tokens to every session and 1,099 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to proofloop-herdr-sol-luna-fable-planr, differing in 9 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…