Borrowing it
Nothing to install: this file belongs to fusebase-dev/fusebase-flow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/fusebase-dev/fusebase-flow/main/.agents/skills/dev-debug-logs/SKILL.mdgit clone --depth 1 https://github.com/fusebase-dev/fusebase-flowWrote 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/fusebase-dev/fusebase-flow/dev-debug-logs)<a href="https://agentmods.dev/skills/fusebase-dev/fusebase-flow/dev-debug-logs"><img src="https://agentmods.dev/badge/skills/fusebase-dev/fusebase-flow/dev-debug-logs/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/fusebase-dev/fusebase-flow/dev-debug-logs"><img src="https://agentmods.dev/badge/skills/fusebase-dev/fusebase-flow/dev-debug-logs.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 | $0.00080 | $0.01415 |
| Opus 5.5 | $0.00032 | $0.00566 |
| Sonnet 5.5 | $0.00016 | $0.00283 |
| Haiku 4.5 | $0.00008 | $0.00142 |
Grade A, and why
dev-debug-logs 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- dev-debug-logs — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dev Debug Logs
Important: This skill is for local development only. For logs from deployed app backends, use the remote-logs skill with
fusebase remote-logscommand.
When an app is run through:
fusebase dev start FEATURE_PATH
the CLI creates a per-session log directory inside the selected app directory:
<app-dir>/logs/dev-<timestamp>/
with these files:
browser-logs.jsonlaccess-logs.jsonlbackend-logs.jsonlfrontend-dev-server-logs.jsonl
Use this skill when debugging the local app runtime. These logs are local development artifacts only.
Which Log File To Read
browser-logs.jsonl
Use for:
console.log/console.erroroutput from the browser- uncaught browser errors
- unhandled promise rejections
- navigation/lifecycle events from the app page
Important:
- It only works when the app is opened through the CLI proxy started by
fusebase dev start - The CLI injects a browser debug script into proxied HTML pages automatically
- Records are JSON Lines; each line is one event
Typical fields:
timestamptypelevelmessageargserrorurlpathname
backend-logs.jsonl
Use for:
- backend stdout/stderr captured during
fusebase dev start - runtime errors printed by an app backend
- startup messages like port binding, env/config issues, and stack traces
Typical fields:
timestampappIdline
Important:
- If the app defines a dedicated backend dev command, the CLI captures that process directly
- If frontend and backend are started together from one
dev.commandusing tools likeconcurrently, the CLI attempts to capture the backend lane into this file as well - This file is line-based output, not structured request logs
access-logs.jsonl
Use for:
- requests made to
/apithrough the local proxy - request/response headers
- request/response bodies for small JSON/text payloads
- proxy failures between the CLI and the app/frontend dev server
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 · 170 lines · 80 tokens per session scan A 9e5eb7ddb879
dev-debug-logs is a skill published in the GitHub repository fusebase-dev/fusebase-flow (9 stars, last pushed 13d ago), licensed MIT. It adds 80 tokens to every session and 1,415 once invoked, about $0.0003 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.
dev-debug-logs compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dev-debug-logsfusebase-dev/fusebase-flow | Skill | 9 | 13d ago | MIT | A | 80 | Claude Code |
| lov-clash-tun-doctorlovstudio/skills | Skill | 72 | yesterday | MIT | A | 93 | Claude Code |
| lov-app-optimizerlovstudio/skills | Skill | 72 | yesterday | MIT | A | 105 | Claude Code |
| lov-runtime-auditlovstudio/skills | Skill | 72 | yesterday | MIT | A | 66 | Claude Code |
| lov-app-professional-designlovstudio/skills | Skill | 72 | yesterday | MIT | A | 79 | Claude Code |
| lov-fix-codex-sessionlovstudio/skills | Skill | 72 | yesterday | MIT | A | 56 | Claude Code |
| lov-align-wechat-uiuxlovstudio/skills | Skill | 72 | yesterday | MIT | A | 70 | Claude Code |