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/latestaiagents/agent-skillsWrote 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/latestaiagents/agent-skills/debug-this)<a href="https://agentmods.dev/commands/latestaiagents/agent-skills/debug-this"><img src="https://agentmods.dev/badge/commands/latestaiagents/agent-skills/debug-this/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/latestaiagents/agent-skills/debug-this"><img src="https://agentmods.dev/badge/commands/latestaiagents/agent-skills/debug-this.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 | $0.00824 |
| Opus 5.5 | $0.00004 | $0.00330 |
| Sonnet 5.5 | $0.00002 | $0.00165 |
| Haiku 4.5 | $0.00001 | $0.00082 |
Grade A, and why
debug-this scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -v https://api.example.com/endpoint How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/debug-this
Structured debugging workflow. Describe the bug and I'll help you find and fix it.
Describe the Bug
Tell me:
- What should happen? (expected behavior)
- What actually happens? (actual behavior)
- When did it start? (recent changes?)
- Error messages? (paste any errors)
Debugging Workflow
Step 1: Reproduce the Bug
First, I need to reliably trigger the bug:
## Reproduction Steps
1. [Step to reproduce]
2. [Step to reproduce]
3. [Bug occurs]
**Reproducible:** Always / Sometimes / Rarely
**Environment:** Dev / Staging / Prod
**Affected users:** All / Some / One
Step 2: Form Hypotheses
Based on symptoms, I'll generate hypotheses ranked by likelihood:
## Hypotheses
1. **[Most likely]** Description
- Evidence for: ...
- Evidence against: ...
- How to verify: ...
2. **[Second likely]** Description
- Evidence for: ...
- Evidence against: ...
- How to verify: ...
3. **[Third likely]** Description
- ...
Step 3: Gather Evidence
For each hypothesis, I'll suggest specific checks:
// Add diagnostic logging
console.log('[DEBUG] Variable state:', { var1, var2, var3 });
// Check database state
SELECT * FROM orders WHERE id = 123;
// Verify API responses
curl -v https://api.example.com/endpoint
// Check logs
grep "ERROR\|Exception" /var/log/app.log | tail -50
Step 4: Isolate the Cause
Narrow down using:
| Technique | When to Use |
|---|---|
| Binary search | Bug in large codebase, use git bisect |
| Simplify inputs | Bug depends on specific data |
| Remove components | Bug might be in dependencies |
| Fresh environment | Bug might be env-specific |
Step 5: Fix and Verify
## Fix
**Root cause:** [What was actually wrong]
**Fix:** [Code change]
**Verification:**
- [ ] Bug no longer reproduces
- [ ] Related features still work
- [ ] Tests pass
- [ ] No new errors in logs
Step 6: Prevent Recurrence
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 · 144 lines · 10 tokens per session scan A 26b0a500fefa
debug-this is a command published in the GitHub repository latestaiagents/agent-skills (5 stars, last pushed 6mo ago), licensed MIT. It adds 10 tokens to every session and 824 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
fdk-fix
Fix all platform validation errors and lint errors in a Freshworks app. Runs fdk validate, identifies fatal errors and lint issues, applies fixes iteratively, and re-validates until all errors are resolved.
self-healing
Automatically detect and recover from errors without interrupting your flow.
fdk-react-create
Create a new Platform 3.0 React Meta app (default UI stack). Uses fdk create react-starter-template or react-meta skeletons with DEW components, metaConfig in manifest.json, and React Router.
fdk-refactor
Reduce function complexity in a Freshworks app to meet cyclomatic complexity ≤ 7 per function. Extracts helper functions, simplifies conditionals, and preserves behavior while improving code quality.
debugger
Systematic debugging with TodoWrite and Memory integration.
fw-setup-uninstall
Uninstall FDK completely — keeps Node.js and nvm (/fw-setup uninstall).