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/Oriolshhh/runware-image-mcpWrote 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/oriolshhh/runware-image-mcp/loop-debug-loop)<a href="https://agentmods.dev/commands/oriolshhh/runware-image-mcp/loop-debug-loop"><img src="https://agentmods.dev/badge/commands/oriolshhh/runware-image-mcp/loop-debug-loop/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/oriolshhh/runware-image-mcp/loop-debug-loop"><img src="https://agentmods.dev/badge/commands/oriolshhh/runware-image-mcp/loop-debug-loop.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 | $0.00000 | $0.00354 |
| Opus 5.5 | $0.00000 | $0.00142 |
| Sonnet 5.5 | $0.00000 | $0.00071 |
| Haiku 4.5 | $0.00000 | $0.00035 |
Grade A, and why
loop-debug-loop 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 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.
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
88% identical to loop-context-compression — 29 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.
What it actually says
/loop-debug-loop — Reproduce, isolate, fix, and verify a failure with bounded evidence-driven iterations.
Follow this ordered workflow. Respect every human-approval gate and stop when instructed.
name: debug-loop
description: Reproduce, isolate, fix, and verify a failure through bounded evidence-driven iterations.
max_iterations: 5
steps:
- name: orient
agent: debugger
instruction: Reuse a supplied context capsule or build one once; record expected and observed behavior.
- name: reproduce
instruction: Reproduce without editing; capture the exact command, environment, failure, and baseline frequency.
- name: investigate
instruction: Minimize the case, trace the narrowest failing path, and update the evidence ledger.
- name: hypothesize
instruction: Rank falsifiable hypotheses and define the next discriminating experiment with predicted outcomes.
- name: experiment-and-fix
instruction: Change one variable; when causation is supported, add a regression test and apply the minimal fix.
- name: verify
instruction: Run the original reproduction, regression, adjacent tests, and configured gates.
gate: gates/default.yml
- name: decide
instruction: Stop on verified success; otherwise begin another pass only below max_iterations, or stop with evidence.
Apply
context-discoverybefore broad scanning: use a supplied context capsule first; otherwise check context frontmatter freshness, read.agent/context/routing.md, load only relevant summaries, and verify critical claims against source.
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 · 31 lines · 0 tokens per session scan A d94e0bb89061
loop-debug-loop is a command published in the GitHub repository Oriolshhh/runware-image-mcp (0 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 354 tokens. A static security scan graded it A with 0 findings. It is 88% identical to loop-context-compression, differing in 29 lines, and is treated as a copy.
Other commands, from other repositories
bugfix
Bug fix workflow: root cause analysis → user review → regression test + fix via TDD.
tdd
Correction de Bug en Mode TDD/BDD.
fix
Correction automatisee des bugs identifies par la QA Recette.
fix-issue
Find and fix issue #$ARGUMENTS. Follow these steps.
do-execute-qa-bugfix
Recebe o caminho de um arquivo de bug em qa-bugs/, analisa a causa raiz, implementa a correção com testes de regressão, valida a suite de testes e atualiza o status do arquivo. Invoque uma vez por bug.
qa
Validate an application against a Gherkin user story by spawning a QA team that drives the running app.