Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add YoungjaeDev/my-claude-plugins/plugin install devWrote 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/youngjaedev/my-claude-plugins/wiring)<a href="https://agentmods.dev/skills/youngjaedev/my-claude-plugins/wiring"><img src="https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/wiring/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/youngjaedev/my-claude-plugins/wiring"><img src="https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/wiring.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 | $0.00135 | $0.05406 |
| Opus 5.5 | $0.00054 | $0.02162 |
| Sonnet 5.5 | $0.00027 | $0.01081 |
| Haiku 4.5 | $0.00014 | $0.00541 |
Grade B, and why
wiring scanned grade B 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 23d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- **mcp config.** When the same server name appears in both `~/.claude.json` and `~/.claude/settings.json`, Claude Code picks one entry whole and discards the other — fields are never merged. The detector compares the en How it starts
The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dev wiring skill
Diagnose whether an existing repository's agent-harness conventions are actually wired up, then fix what the user approves.
Sibling of new: new bootstraps an empty directory and hard-aborts on a non-empty one. wiring is the inverse — it only makes sense on a repo that already exists.
Contract
- Detection is read-only.
scripts/project_state.shnever writes. Run it first, always. - Nothing is fixed before approval. Present the full report, then a single
AskUserQuestiongate. - Delegate, do not reimplement. Every remediation that needs judgment routes to the skill that owns it. Only mechanical, reversible edits are applied here.
- Absent tooling is not a defect. A missing optional CLI is never a
FAIL. Forgws-syncthe exact verdict —ASK,SKIP,INFO, or aWARNwhen a live.gws-sync.jsonoutlives its CLI — comes from the table in "gws-sync is a two-step ASK", never from the CLI's absence alone. - A decision is not a defect. Some axes have no correct answer the filesystem can know — whether this project wants a git remote, whether its deliverables belong on a shared Drive. Those report
ASK, are put to the user once, and the answer is persisted so the next run stays quiet. An axis that barks the same un-answerable warning every run trains the user to ignore the ones that matter.
Verdict classes
| Class | Means | Next run |
|---|---|---|
FAIL |
broken, or losing data | keeps failing until fixed |
WARN |
works but degraded | keeps warning until fixed |
ASK |
a decision nobody has made yet — not a defect | silent once answered |
INFO |
worth seeing, no action implied | always shown |
SKIP |
optional and not adopted | silent |
OK |
healthy | one line |
Answers file
ASK answers live in .claude/state/wiring.json (gitignored, alongside review-loop-*.json). Values are machine-local — a Drive folder id is not the same on another clone — so they do not belong in a committed file. CLAUDE.md carries only a pointer to this path, never the values.
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.
- 23d ago Changed 6ebb9d831a69
- 25d ago Changed · -4 lines · -12 tokens per session 905f9b7f5449
- 1mo ago Changed aa895cf0b772
- 1mo ago First seen · 223 lines · 147 tokens per session scan B 8108dc1d8b77
wiring is a skill published in the GitHub repository YoungjaeDev/my-claude-plugins (2 stars, last pushed today), licensed MIT. It adds 135 tokens to every session and 5,406 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
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…