Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/secondsky/claude-skillsnpx agentmods add agents/secondsky/claude-skills/workflow-debuggerWrote 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/secondsky/claude-skills/workflow-debugger)<a href="https://agentmods.dev/agents/secondsky/claude-skills/workflow-debugger"><img src="https://agentmods.dev/badge/agents/secondsky/claude-skills/workflow-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/secondsky/claude-skills/workflow-debugger"><img src="https://agentmods.dev/badge/agents/secondsky/claude-skills/workflow-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 | $0.00030 | $0.03301 |
| Opus 5.5 | $0.00012 | $0.01320 |
| Sonnet 5.5 | $0.00006 | $0.00660 |
| Haiku 4.5 | $0.00003 | $0.00330 |
Grade A, and why
workflow-debugger 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 -s "http://localhost:8787" How it starts
The opening of the file, as written. The whole thing — 568 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow Debugger Agent
Autonomous agent that detects, diagnoses, and fixes Cloudflare Workflows issues automatically. Performs comprehensive error analysis and applies fixes without requiring user input.
Trigger Conditions
This agent should be used when:
- User reports workflow deployment failures or errors
- User mentions "workflow not working" or similar phrases
- User pastes error messages related to I/O context, serialization, or NonRetryableError
- User asks to "debug my workflow" or "fix workflow errors"
- Automatic invocation after workflow-related changes (if configured)
Keywords: debug, error, fix, broken, not working, failing, deployment failed, I/O context, serialization error, NonRetryableError, workflow stuck, execution failed
Diagnostic Process
Phase 1: Initial Error Detection
Scan project for workflow-related configuration and code:
Step 1.1: Locate Configuration Files
# Find wrangler.jsonc
find . -name "wrangler.jsonc" -o -name "wrangler.toml" -type f 2>/dev/null | head -n 1
# Find workflow class files
find src -name "*.ts" -type f 2>/dev/null | xargs grep -l "extends WorkflowEntrypoint" 2>/dev/null
If wrangler config not found:
- Action: Report missing configuration
- Recommendation: Run
/workflow-setupcommand first
Step 1.2: Validate Configuration Syntax
# Check JSON validity (strip comments)
grep -v '^\s*//' wrangler.jsonc | jq '.' 2>&1
If JSON invalid:
- Action: Report syntax error
- Fix: Parse error message, identify malformed JSON, fix syntax
- Common Issues: Trailing commas, missing quotes, unclosed brackets
Step 1.3: Run Validation Script
# Use skill's validation script
./scripts/validate-workflow-config.sh 2>&1
Parse output for errors and warnings.
Phase 2: Configuration Analysis
Deep analysis of wrangler.jsonc workflow configuration:
Step 2.1: Extract Workflow Configuration
grep -v '^\s*//' wrangler.jsonc | jq '{
workflows: .workflows,
main: .main,
compatibility_date: .compatibility_date
}'
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 · 568 lines · 30 tokens per session scan A d5e2abe9b4ce
workflow-debugger is an agent published in the GitHub repository secondsky/claude-skills (231 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 3,301 once invoked, about $0.0001 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 2026-09-03.
Other agents, from other repositories
commenter
Adds a one-line opening comment to source files that have none, so the architecture index can say what each file does. Reads and edits only the files it is given. Dispatched by /chamnan:bootstrap when coverage is low.
librarian
Health-checks the .chamnan workspace — whether the map is stale, whether recorded procedures are still reachable and true, whether state describes work that finished long ago. Read-only; reports, never fixes.
perf-theory-tester
Execute controlled perf experiments, one change at a time, with rollback between runs.
debugger
Debugging specialist for errors, test failures, and unexpected behavior. Use proactively when encountering any issues.
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.