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 agentmods add skills/dowwie/tasker/runtime-loggernpx skills add Dowwie/tasker --skill runtime-loggergit clone --depth 1 https://github.com/Dowwie/taskerWhat 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 | $0.00022 | $0.01028 |
| Opus 5 | $0.00011 | $0.00514 |
| Sonnet 5 | $0.00004 | $0.00206 |
| Haiku 4.5 | $0.00002 | $0.00103 |
Grade B, and why
runtime-logger scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
tail -f .claude/logs/activity.log How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Runtime Activity Logger
Log key activities to .claude/logs/activity.log using bash as you work. This creates a trace of agent reasoning and actions analogous to info-level logging in deterministic code.
Setup
Before starting any task, ensure the log directory exists:
mkdir -p .claude/logs
Log Format
Use this consistent format for all log entries:
echo "[$(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
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.
- 2d ago First seen · 117 lines · 22 tokens per session scan B 42cb2d6fd0fe
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.
Other skills, from other repositories
debug
Run /debug to find and fix a bug's root cause: a test failing for an unclear reason, /check verify finding a failure, or behavior being wrong. Runs a reproduce, localize, hypothesize, test, fix, verify loop, makes the minimal fix, and hands a regression test to /test. No features, no extra refactors.
auth-security
Secure authentication and authorization when credentials, sessions, roles, or permissions change.
red-team-adversarial
Adversarial security and resilience analysis — auto-triggered during /review and /test based on task classification. Provides attack surface analysis, boundary testing, auth bypass attempts, dependency chain attacks, and Beast Mode stress testing.
karpathy-principles
Behavioral guidelines to reduce common LLM coding mistakes — Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution.
database-design
Design schemas and migrations when persistent data structures change.
verification-before-completion
Enforce "no evidence = no completion"; run Gate Function verification before declaring done.