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 skills/eveld/claude/debug-systematicallynpx skills add eveld/claude --skill debug-systematicallygit clone --depth 1 https://github.com/eveld/claudeWhat 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 | $0.00022 | $0.01123 |
| Opus 5 | $0.00011 | $0.00562 |
| Sonnet 5 | $0.00004 | $0.00225 |
| Haiku 4.5 | $0.00002 | $0.00112 |
Grade A, and why
debug-systematically 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug Systematically
Follow a structured debugging process when encountering errors or unexpected behavior.
Debugging Process
1. Reproduce
Goal: Confirm the error consistently occurs
- Run the failing command/test again
- Document exact steps to reproduce
- Note any error messages verbatim
- Check if error is consistent or intermittent
Example:
# Reproduce the error
make test
# Document output
Error: undefined method 'foo' on line 42
2. Isolate
Goal: Narrow down to specific component/function
- Identify which component is failing
- Remove unrelated code to isolate issue
- Check if error occurs with minimal input
- Use binary search to find breaking change
Example:
# Test individual components
go test ./pkg/auth/handler_test.go -v -run TestLogin
# Isolate to specific function
go test ./pkg/auth -v -run TestLogin/valid_credentials
3. Hypothesize
Goal: Form testable theories about the cause
- Based on error message, what could cause this?
- What changed recently that might affect this?
- What assumptions might be wrong?
- What edge cases aren't handled?
Examples:
- Hypothesis 1: Nil pointer - missing initialization
- Hypothesis 2: Type mismatch - wrong function signature
- Hypothesis 3: Race condition - concurrent access
4. Test Hypotheses
Goal: Verify each hypothesis systematically
- Test one hypothesis at a time
- Add logging/debugging to verify assumptions
- Check related code for similar patterns
- Look at test failures for clues
Example:
// Test hypothesis 1: nil pointer
if handler.service == nil {
log.Printf("DEBUG: service is nil")
}
// Test hypothesis 2: check types
log.Printf("DEBUG: user type=%T, expected=*User", user)
5. Fix
Goal: Apply fix and verify it resolves the issue
- Implement the fix for confirmed root cause
- Run the originally failing test/command
- Verify fix doesn't break other functionality
- Clean up any debug logging
Example:
// Fix: Initialize service before use
func NewHandler() *Handler {
return &Handler{
service: NewAuthService(), // was missing
}
}
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 · 204 lines · 22 tokens per session scan A 8c960716ef57
debug-systematically is a skill published in the GitHub repository eveld/claude (10 stars, last pushed 6mo ago), licensed MIT. It adds 22 tokens to every session and 1,123 once invoked, about $0.0001 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 skills, from other repositories
code-indexing-pipeline
How Infigraph turns source into a graph — adding a language (tree-sitter vs ANTLR grammar-plugin), cross-file call resolution, SCIP compiler-grade enrichment, and file-watch/reindex triage. Use when adding language support, debugging unresolved calls or SCIP import, or triaging stale index/watcher issues.
review-pr-against-issue
Review one or more PRs against the GitHub issue(s) they claim to fix, including fetching PR branches directly when gh can't reach github.com (e.g. gh is authenticated to an enterprise host instead). Use whenever asked "does this PR fix issue.
analysis-subsystems
How Infigraph's multi-repo/group mode and taint analysis work internally — HTTP contract extraction heuristics, cross-service edge linking, combined-graph merge, remote mode, plus taint's line-based tracking and sanitizer heuristic. Use when working on crates/infigraph-core/src/multi/ or src/taint/, or investigating…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
golden-rss
Use when testing the rss golden build.
omh-code-review
This is a Hermes-native code-review workflow skill.