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/saajunaid/caddis-pluginWrote 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/saajunaid/caddis-plugin/debug-help)<a href="https://agentmods.dev/commands/saajunaid/caddis-plugin/debug-help"><img src="https://agentmods.dev/badge/commands/saajunaid/caddis-plugin/debug-help/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/saajunaid/caddis-plugin/debug-help"><img src="https://agentmods.dev/badge/commands/saajunaid/caddis-plugin/debug-help.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 | $0.00010 | $0.01191 |
| Opus 5.5 | $0.00004 | $0.00476 |
| Sonnet 5.5 | $0.00002 | $0.00238 |
| Haiku 4.5 | $0.00001 | $0.00119 |
Grade A, and why
debug-help 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug Help Prompt
Purpose
Structure debugging requests to efficiently identify and resolve issues.
Pipeline Boundary (when used with the junai pipeline)
If .github/pipeline-state.json exists:
- Produce a diagnostic brief and a project-ready troubleshooting prompt.
- Do not include pipeline-stage transitions, gate instructions, or pipeline-state edits.
- Do not provide direct handoff routing.
- End with: "Use
@Orchestratorto route this troubleshooting brief."
Input Required
- Error message or symptom
- Code context
- What was tried
Template
I need help debugging an issue:
## The Problem
**What's happening**: {symptom_description}
**Expected behavior**: {what_should_happen}
**Error message** (if any):
{error_message}
## Context
**File/Function**: {location}
**Relevant code**:
```python
{code_snippet}
When it happens: {trigger_conditions}
Environment:
- Python version: {version}
- OS: {os}
- Relevant packages: {packages}
What I've Tried
- {attempt_1}
- {attempt_2}
- {attempt_3}
Additional Context
{any_other_info}
Please help me:
- Identify the root cause
- Suggest a fix
- Explain why the issue occurred
## Example
### Input
I need help debugging an issue:
The Problem
What's happening: Dashboard crashes when loading complaints data
Expected behavior: Dashboard should display the complaints table
Error message:
pyodbc.OperationalError: ('08001', '[08001] [Microsoft][ODBC Driver 17 for SQL Server]
Named Pipes Provider: Could not open a connection to SQL Server [53]. (53)')
Context
File/Function: app/pages/dashboard.py, load_complaints_data()
Relevant code:
@st.cache_data(ttl=timedelta(minutes=15))
def load_complaints_data():
adapter = DatabaseAdapter()
return adapter.fetch_dataframe(
"SELECT * FROM complaints WHERE status = 'open'"
)
When it happens: On first page load, after recent server restart
Environment:
- Python version: 3.11.4
- OS: Windows Server 2019
- Relevant packages: pyodbc 4.0.39, streamlit 1.28.0
What I've Tried
- Checked SQL Server is running (it is)
- Tested connection string in SQL Server Management Studio (works)
- Restarted the Streamlit app
Additional Context
This was working yesterday. Server was restarted overnight for updates.
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 · 212 lines · 10 tokens per session scan A a5a0aedd3857
debug-help is a command published in the GitHub repository saajunaid/caddis-plugin (0 stars, last pushed today), licensed MIT. It adds 10 tokens to every session and 1,191 once invoked, about $0.0000 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 2026-09-09.
Other commands, from other repositories
debug-screen
Diagnose why the current screen is broken, showing unexpected content, or crashing. Gathers parallel evidence from all layers and applies a targeted fix.
self-healing
Automatically detect and recover from errors without interrupting your flow.
test-feature
Test a React Native feature on the running simulator/emulator. Verifies UI, user flows, and internal state. Generates a persistent Maestro test file.
specify
Command dispatcher for specify.
observe
Show the observability web UI URL (it autostarts with the session); stop or restart it.
accept
Command dispatcher for accept.