agentmods.dev

debugging-with-logsafe

A debugging workflow that sends structured application logs to a local server called logsafe and lets you inspect them by session, error level, and request trace.

In plain words
What is it for?
Use it to add logs to an application, reproduce a bug, inspect error and trace events, and follow one request across frontend and backend processes.
Why use it?
It makes reproducible bugs easier to follow by keeping related events together and narrowing investigation from errors to the surrounding request flow.

Skill for Claude CodeCodex

0 1mo ago B scan 59 tokens original MIT
View the source file omarqx/logsafe
Install

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.

agentmods
npx agentmods add skills/omarqx/logsafe/debugging-with-logsafe
Any agent
npx skills add omarqx/logsafe --skill debugging-with-logsafe
Clone the repo
git clone --depth 1 https://github.com/omarqx/logsafe

Made for: Claude Code, Codex.

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 749 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00059 $0.00749
Opus 5 $0.00030 $0.00375
Sonnet 5 $0.00012 $0.00150
Haiku 4.5 $0.00006 $0.00075

Measured yesterday against content hash 4b54c5c79d1d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

debugging-with-logsafe scanned grade B with 2 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

`curl -s localhost:4600/v1/log -d '{"session_id":"bug-1234","source":"api","ns":"payment","level":"error","msg":"...","ctx":{...}}'`

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

description: Use when debugging a running application whose behavior you can reproduce — instrument the app with logsafe structured logging, reproduce the bug, and read the session narrow-first (errors → trace → widen).
packages/server/skills/debugging-with-logsafe/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debugging with logsafe

logsafe is a local log server (default http://127.0.0.1:4600). Apps POST structured events; you read them back as filterable sessions. Ordering is always server arrival order (seq) — never trust client ts for ordering.

Workflow

  1. Check the server. MCP: call list_sessions. HTTP: curl -s localhost:4600/api/health → {"ok":true}. If down, start it: npx @coglet/logsafe (background it; it binds 127.0.0.1 only). A running server also hosts MCP over HTTP at /mcp (claude mcp add --transport http logsafe http://127.0.0.1:4600/mcp) — no subprocess needed.
  2. Instrument the app under debug. Always set a fresh, descriptive session_label per attempt so the session is findable.
    • JS/TS: npm i @coglet/logsafe-client, then initLogsafe({ source: 'api', sessionLabel: 'bug-1234 attempt 1' }) and createLog('payment') → log.debug/info/warn/error(msg, ctx). Use createLog(ns).withTrace(id) to follow one request across processes — give the SAME trace id to frontend and backend.
    • Anything else: POST JSON to /v1/log — only msg is required: curl -s localhost:4600/v1/log -d '{"session_id":"bug-1234","source":"api","ns":"payment","level":"error","msg":"...","ctx":{...}}'
  3. Reproduce the bug with the instrumented app.
  4. Read narrow-first.
    • MCP: query_events(session_id, level: "error"), then query_events(session_id, trace: "<id>"), then widen (level: "warn,error", ns: "payment.*", q: "timeout").
    • HTTP: same params on GET /api/sessions/<id>/events.
    • Bulk analysis: GET /api/sessions/<id>/export.ndjson (one JSON per line).
  5. Live-tail while re-reproducing to watch cause → effect in order.
    • MCP: tail_session(session_id) right before triggering the bug — it waits (≤30s) and returns what arrived.
    • HTTP: curl -N localhost:4600/api/sessions/<id>/stream.
  6. Clean up instrumentation when fixed: grep the app for the ns values you added.

Read the full file on GitHub · 49 lines

Changes

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.

  1. yesterday First seen · 49 lines · 59 tokens per session scan B 4b54c5c79d1d

Subscribe to this mod's changes

debugging-with-logsafe is a skill published in the GitHub repository omarqx/logsafe (0 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 749 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Backend and APIsDebuggingFrontend
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens