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 commands/laaibaqasim/productivity-kit/loggergit clone --depth 1 https://github.com/laaibaQasim/productivity-kitWrote 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/commands/laaibaqasim/productivity-kit/logger)<a href="https://agentmods.dev/commands/laaibaqasim/productivity-kit/logger"><img src="https://agentmods.dev/badge/commands/laaibaqasim/productivity-kit/logger.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00860 |
| Opus 5 | $0.00000 | $0.00430 |
| Sonnet 5 | $0.00000 | $0.00172 |
| Haiku 4.5 | $0.00000 | $0.00086 |
Grade A, and why
logger 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Get Summary of daily logs
description: >- You are an expert at summarizing work and estimating task durations. Given raw session log data, you can instantly identify patterns, group related actions into meaningful tasks, and produce a clean, human-readable daily summary with accurate time estimates. You cut through noise, merge related entries, and deliver exactly what someone needs for a standup or end-of-day review.
/logger
Generate a daily work summary from session log files.
Instructions
-
Ask the user for a date, or default to today (YYYY-MM-DD format).
-
Find the log file for that date.
- Read
.cursor/config.json(or.claude/config.json) to getsession_tracking.store_directory(default:work-logs/) andstore_name_prefix(default:session-work-log). - The file is at:
<store_directory>/<prefix>-<YYYY-MM-DD>.json - If the file does not exist, tell the user and stop.
- Read
-
Parse all sessions from the JSON file.
- Each session has:
started_at,ended_at,duration_minutes,tool,branch_name,session_logs(array of structured log entries). - Each
session_logsentry has:captured_at,user_intent,prompt_summary,what_i_did,open_issues,next_best_step. - Older files may have
summary_bullets(array of strings) instead ofsession_logs.
- Each session has:
-
Group related log entries into 4–5 major tasks.
- Read every
user_intentandwhat_i_didacross all sessions. - Cluster entries that are part of the same logical effort (e.g. multiple edits to the same feature, a refactor that spans hooks, a documentation pass).
- Use your judgment: consecutive entries about the same topic or files belong together.
- Ignore trivial noise (repeated retries, rule-reading, hello-world test files) unless they contributed meaningfully.
- Read every
-
Estimate time for each task.
- Use
captured_attimestamps within a session andstarted_at/ended_atacross sessions. - For entries within one session: time is roughly from the first
captured_atof that group to the next group's firstcaptured_at(orended_atif it's the last group). - For entries spanning multiple sessions: sum the relevant session
duration_minutes. - If timestamps overlap or gaps are unclear, estimate and mark as "~approx".
- Do NOT double-count time across overlapping Claude + Cursor sessions.
- Use
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.
- 4d ago First seen · 78 lines · 0 tokens per session scan A 43019a230bce
logger is a command published in the GitHub repository laaibaQasim/productivity-kit (4 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 860 tokens. 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.
Other commands, from other repositories
create-hook
Create hooks with brainstorming and security-first design.
evaluate-skill
Manually evaluate a recent skill execution to record qualitative feedback.
VibeGuard: Stats
View hooks trigger statistics - interception/warning/release times and reason analysis.
oss
Daily OSS contribution check - uses CLI with --json for structured data.
setup-oss
Configure OSS autopilot preferences.
nyann:diff-profile
Compare two nyann profiles side-by-side and show what changes between them: hooks, branching, CI, documentation, extras, governance. Useful before switching profiles to understand the impact.