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 skills add Cristhianzl/claude-skills-czl --skill debugging-agent-runsgit clone --depth 1 https://github.com/Cristhianzl/claude-skills-czlWrote 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/skills/cristhianzl/claude-skills-czl/debugging-agent-runs)<a href="https://agentmods.dev/skills/cristhianzl/claude-skills-czl/debugging-agent-runs"><img src="https://agentmods.dev/badge/skills/cristhianzl/claude-skills-czl/debugging-agent-runs/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/skills/cristhianzl/claude-skills-czl/debugging-agent-runs"><img src="https://agentmods.dev/badge/skills/cristhianzl/claude-skills-czl/debugging-agent-runs.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 | $0.00084 | $0.00750 |
| Opus 5 | $0.00042 | $0.00375 |
| Sonnet 5 | $0.00017 | $0.00150 |
| Haiku 4.5 | $0.00008 | $0.00075 |
Grade A, and why
debugging-agent-runs 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 12d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debugging agent runs
When the problem is the run, not the code: the agent keeps trying variations of the same thing, talks itself in circles, or acts on what it remembers instead of what's true. This skill is a recovery loop to break that. Be honest: it's a discipline you apply — it can't magically fix a stuck process.
Read first (always)
List learnings/ and read anything relevant — past failure modes specific to this project belong there.
Recognize the failure mode
| Symptom | Likely cause |
|---|---|
| Same action retried with slightly reworded prompts | Loop / no new information between attempts |
| Output truncated, "forgetting" earlier context | Context overflow → compact or restart with a tighter scope |
| Repeated 429 / timeouts | Rate limit → back off, batch, slow down |
| Edits land on the wrong branch/files; conflicts | Branch / diff drift → re-verify git state |
| Confident claims that don't match reality | Stale state → trusting memory over the world |
| Scope keeps widening while nothing lands | Scope creep → shrink to one verifiable thing |
The recovery loop
Run these in order — most stuck runs are fixed by step 1–2:
- Restate the real objective in one sentence. If you can't, that's the bug. Re-anchor to the user's actual goal, not the sub-task you spiraled into.
- Verify world state — don't trust memory. Re-read the files,
git status/diff, and the actual test/command output. The model's recollection is often stale; reality isn't. - Shrink the failing scope. Reduce to the smallest reproduction or the single failing unit. Big scope hides the cause.
- Run one discriminating check — the single command/test whose result tells you which branch of the problem you're in. Don't guess; get one new bit of information.
- Only then retry — and change the approach, not just the wording. If the new info didn't change your plan, you're still looping.
Anti-patterns
- Retrying the same action three times with reworded prompts (no new information = a loop).
- Trusting your memory of the code/state instead of re-reading it.
- Widening scope when stuck (the opposite of step 3).
- Fabricating that something "should now work" without a check that proves it.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 55 lines · 84 tokens per session scan A 01112788cd97
debugging-agent-runs is a skill published in the GitHub repository Cristhianzl/claude-skills-czl (5 stars, last pushed yesterday), licensed MIT. It adds 84 tokens to every session and 750 once invoked, about $0.0004 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
lcx-report-bug
Create a high-signal bug issue or PR in the repo that owns the defect. Use this whenever the user asks to report, file, open, or triage a LazyCodex, lazycodex-ai, omo-codex, Codex plugin, or upstream Codex CLI bug, especially when they need source-backed root cause, reproduction steps, fix guidance, and GitHub routing.
ast-grep
Searches and rewrites code by AST shape across 25 languages. Use when the target is a syntax pattern (every call/class/import shaped like X, a codemod, a YAML rule) rather than literal text; for plain strings, comments, or filenames, use rg.
debugging
Runs a hypothesis-driven debugging loop across any language or binary, escalating to orthogonal oracle angles and locking the fix with a failing test. Use for crashes, silent failures, hangs, wrong responses, memory leaks, async misbehavior, or reverse engineering.
lcx-doctor
Diagnose LazyCodex and Codex CLI installation health against the latest sources. Use whenever the user asks for a doctor or health check, says LazyCodex, lazycodex-ai, omo-codex, or Codex behaves oddly after an install, update, or config change, suspects a stale, drifted, or broken setup, or wants the local install…
remove-deadcode
Remove unused code from this project with ultrawork mode, LSP-verified safety, atomic commits. Triggers: remove dead code, dead code, cleanup, remove unused.
lsp
Use when Codex needs language-server diagnostics, definitions, references, symbols, or rename safety checks in the current workspace.