runtime-logger

A task activity logger that writes timestamped progress and outcome messages to a project log file.

In plain words
What is it for?
Recording task starts and completions, important tool actions, technical decisions, unexpected situations, and errors in .claude/logs/activity.log.
Why use it?
It creates a written record of what happened during a task, which helps when reviewing decisions or investigating failures.

Skill for Claude CodeCodex

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/dowwie/tasker/runtime-logger
Any agent
npx skills add Dowwie/tasker --skill runtime-logger
Clone the repo
git clone --depth 1 https://github.com/Dowwie/tasker

Made for: Claude Code, Codex.

Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,028 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00022 $0.01028
Opus 5 $0.00011 $0.00514
Sonnet 5 $0.00004 $0.00206
Haiku 4.5 $0.00002 $0.00103

Measured 2d ago against content hash 42cb2d6fd0fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

runtime-logger 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 2d 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.

tail -f .claude/logs/activity.log
internal/skills/runtime-logger/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Runtime Activity Logger

Log key activities to .claude/logs/activity.log using bash as you work. This creates a trace of agent reasoning and actions analogous to info-level logging in deterministic code.

Setup

Before starting any task, ensure the log directory exists:

mkdir -p .claude/logs

Log Format

Use this consistent format for all log entries:

echo "[$(date -Iseconds)] [LEVEL] phase: message" >> .claude/logs/activity.log

Log Levels

Level Use For
INFO Normal operations, progress updates, decisions
DEBUG Detailed technical information when troubleshooting
WARN Unexpected situations that don't block progress
ERROR Failures that affect task completion

When to Log

Task Lifecycle

  • Task start: Log the goal and planned approach
  • Task completion: Log summary, outcome, and any artifacts created

Tool Usage

  • Before significant tool use: Log what tool and why
  • After tool use: Log outcome (success/failure, key findings)

Decision Points

  • Architectural choices: Log reasoning for design decisions
  • Branch points: Log why one approach was chosen over alternatives
  • Assumptions: Log any assumptions being made

Subagent Activity

  • Delegation: Log task being delegated and to which subagent
  • Completion: Log subagent results when they return

Examples

Starting a Task

echo "[$(date -Iseconds)] [INFO] start: Beginning refactoring task for payment module" >> .claude/logs/activity.log
echo "[$(date -Iseconds)] [INFO] planning: Will analyze current structure, identify patterns, then apply Strategy pattern" >> .claude/logs/activity.log

Tool Usage

echo "[$(date -Iseconds)] [INFO] tool: Reading src/payments/processor.py to understand current implementation" >> .claude/logs/activity.log
echo "[$(date -Iseconds)] [INFO] tool-result: Found 3 payment types with duplicated validation logic" >> .claude/logs/activity.log

Read the full file on GitHub · 117 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. 2d ago First seen · 117 lines · 22 tokens per session scan B 42cb2d6fd0fe

Subscribe to this mod's changes

runtime-logger is a skill published in the GitHub repository Dowwie/tasker (19 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 22 tokens to every session and 1,028 once invoked, about $0.0001 per session on Opus 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 2026-08-30.