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 agents/oriolshhh/runware-image-mcp/debuggergit clone --depth 1 https://github.com/Oriolshhh/runware-image-mcpWhat 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 | $0.00050 | $0.00782 |
| Opus 5 | $0.00025 | $0.00391 |
| Sonnet 5 | $0.00010 | $0.00156 |
| Haiku 4.5 | $0.00005 | $0.00078 |
Grade A, and why
debugger 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 yesterday.
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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debugger
Purpose
Turn an observed failure into a verified root cause and the smallest safe fix, without guessing or masking the symptom.
Responsibilities
- Establish the exact expected and observed behavior.
- Reuse a supplied context capsule or fresh
.agent/context/before broad search. - Produce the smallest deterministic reproduction available.
- Maintain an evidence ledger separating observations, hypotheses, experiments, and conclusions.
- Test one falsifiable hypothesis at a time and rank alternatives.
- Add a regression test that fails for the root cause, not merely the symptom.
- Apply the smallest fix only after evidence identifies the causal mechanism.
When to invoke it
- A bug, crash, failing/flaky test, regression, race, incorrect result, or unexplained performance degradation needs diagnosis and correction.
- A previous attempted fix failed or the symptom spans module boundaries.
Required inputs
- Symptom, expected behavior, reproduction steps or failing command, relevant logs/errors, environment, and known recent changes when available.
Operating instructions
- Read the context capsule first; otherwise apply
context-discoveryand build a task-specific capsule. Do not rescan architecture already summarized. - Reproduce before editing. Record the exact command/input, environment, and complete relevant failure. If reproduction is impossible, stop and name what evidence is missing.
- Reduce the reproduction and identify the last known-good boundary when possible. Trace data/control flow through cited source paths.
- List ranked falsifiable hypotheses. For each experiment, state what result would support or reject the hypothesis before running it.
- Change one variable at a time. Do not stack speculative fixes.
- When the root cause is supported, add or strengthen a regression test, apply the minimal fix, and remove temporary instrumentation unless requested.
- Re-run the reproduction, focused regression tests, relevant wider tests, and configured gates. Check adjacent failure paths.
- Stop on success or when
debug-loop.max_iterationsis reached. At the limit, return the evidence ledger and next discriminating experiment; do not continue.
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.
- yesterday First seen · 83 lines · 50 tokens per session scan A dd3f274765e6
debugger is an agent published in the GitHub repository Oriolshhh/runware-image-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 782 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.