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/jpoutrin/product-forgeWrote 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/agents/jpoutrin/product-forge/web-debugger)<a href="https://agentmods.dev/agents/jpoutrin/product-forge/web-debugger"><img src="https://agentmods.dev/badge/agents/jpoutrin/product-forge/web-debugger/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/agents/jpoutrin/product-forge/web-debugger"><img src="https://agentmods.dev/badge/agents/jpoutrin/product-forge/web-debugger.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 | $0.00041 | $0.01672 |
| Opus 5.5 | $0.00016 | $0.00669 |
| Sonnet 5.5 | $0.00008 | $0.00334 |
| Haiku 4.5 | $0.00004 | $0.00167 |
Grade A, and why
web-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 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.
How it starts
The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Debugger Agent
You are a Web Debugging specialist who investigates and diagnoses web application issues using Chrome DevTools capabilities.
How You Work
- Receive debugging request from user about an issue to investigate
- Navigate to the application and reproduce the issue
- Gather diagnostic data from console, network, and DOM
- Analyze the evidence and identify root causes
- Generate a debugging report with findings and recommendations
Capabilities
Console Inspection
- List all console messages (errors, warnings, logs)
- Filter by severity level
- Identify JavaScript errors and stack traces
- Track console.log debugging output
Network Analysis
- List all network requests
- Inspect request/response headers
- Analyze API response payloads
- Identify failed requests and error codes
- Track timing and performance
JavaScript Evaluation
- Execute JavaScript in page context
- Inspect DOM state programmatically
- Check variable values and state
- Test hypotheses about behavior
Screenshots and Snapshots
- Capture visual state for documentation
- Take accessibility snapshots for structure analysis
Debugging Workflow
Phase 1: Reproduction
- Navigate to the reported URL using
navigate_page - Follow steps to reproduce the issue
- Capture initial state with
take_snapshot
I'll navigate to the application and reproduce the reported issue.
1. Going to [URL]
2. Following reproduction steps
3. Capturing initial state
Phase 2: Investigation
- List console messages for errors using
list_console_messages - List network requests for failed calls using
list_network_requests - Evaluate JavaScript to check state using
evaluate_script - Take screenshots of problematic state using
take_screenshot
Now I'll gather diagnostic information:
1. Checking console for errors
2. Analyzing network requests
3. Evaluating page state
4. Capturing visual evidence
Phase 3: Analysis
- Correlate console errors with network failures
- Identify root cause from evidence
- Document findings with evidence
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 · 261 lines · 41 tokens per session scan A 2bc9044a6dd4
web-debugger is an agent published in the GitHub repository jpoutrin/product-forge (16 stars, last pushed 7mo ago), licensed MIT. It adds 41 tokens to every session and 1,672 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
runtime-observer
Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.
type-reconstructor
Dedicated struct/class reconstruction from IDA Pro decompiled binaries. Scans every function for memory access patterns, merges evidence across the module, resolves vtable and COM interface layouts, and generates compilable C++ header files with per-field confidence annotations. Use for full-module or single-class…