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 Aibier/claude-em-toolkit --skill debug-with-plangit clone --depth 1 https://github.com/Aibier/claude-em-toolkitWrote 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/aibier/claude-em-toolkit/debug-with-plan)<a href="https://agentmods.dev/skills/aibier/claude-em-toolkit/debug-with-plan"><img src="https://agentmods.dev/badge/skills/aibier/claude-em-toolkit/debug-with-plan/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/aibier/claude-em-toolkit/debug-with-plan"><img src="https://agentmods.dev/badge/skills/aibier/claude-em-toolkit/debug-with-plan.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 | $0.00041 | $0.00417 |
| Opus 5.5 | $0.00016 | $0.00167 |
| Sonnet 5.5 | $0.00008 | $0.00083 |
| Haiku 4.5 | $0.00004 | $0.00042 |
Grade A, and why
debug-with-plan 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 2mo 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.
What it actually says
Debugging in Plan Mode
Investigation and fix-proposal are kept separate from execution. Root-cause first, propose second, implement only after explicit approval.
Steps
-
Reproduce first. Get the exact failing command/input/conditions before theorizing. If you can't reproduce it, say so — don't guess at a fix for something you haven't observed.
-
Stay in Plan Mode for the investigation. Read code, run read-only commands (logs,
git log/git blameon the suspect area, test runs), form a hypothesis — but make no edits yet. -
Find the root cause, not the symptom. Ask "why" until you hit something that, if changed, would have prevented the bug from ever being possible — not just the line where it surfaced.
-
Propose, don't just fix. Lay out:
## Root cause <what's actually wrong, and why it produces the observed symptom> ## Proposed fix <the change, and why this is the right altitude — fixing the cause, not papering over the symptom> ## Alternatives considered <if there were other viable approaches, name them and why you didn't pick them> ## Regression test <what test would have caught this, and that you'll add it> -
Exit Plan Mode and implement only after the user approves the proposal.
Notes
- Resist the urge to start editing the moment you spot something suspicious — confirm it's the cause, not a plausible one.
- A fix without a regression test isn't done — see [[impact-review]] for reviewing the blast radius of the change once it's written.
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.
- 2mo ago First seen · 48 lines · 41 tokens per session scan A d2a01a6ec943
debug-with-plan is a skill published in the GitHub repository Aibier/claude-em-toolkit (5 stars, last pushed 5mo ago), licensed MIT. It adds 41 tokens to every session and 417 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
ci-fixer
CI failures - read error, minimal fix, verify.
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
diagnosing-missing-recordings
Diagnoses why a session recording is missing or was not captured. Use when a user asks why a session has no replay, why recordings aren't appearing, or wants to troubleshoot session replay capture issues for a specific session ID or across their project. Covers SDK diagnostic signals, project settings, sampling…