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/affectionatec/agentic-engineering/status-trackernpx skills add affectionatec/agentic-engineering --skill status-trackergit clone --depth 1 https://github.com/affectionatec/agentic-engineeringWhat 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 | $0.00098 | $0.02312 |
| Opus 5 | $0.00049 | $0.01156 |
| Sonnet 5 | $0.00020 | $0.00462 |
| Haiku 4.5 | $0.00010 | $0.00231 |
Grade A, and why
status-tracker 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 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.
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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Status Tracker — Project Status & Progress
Core constraint: This file is the Agent's memory. Read it first, update it last. Every session.
Quick Reference
| Use when | Start of every session (read first), end of every session (update last) |
| Skip when | Never — every session reads docs/status.md before any other action |
| Output | docs/status.md — live, with append-only handoff log |
| Sequence | Created when IMPL PLAN starts; updated every session forever |
| Iron rule | Handoff log is append-only, newest first. Never edit past entries. |
| Sibling skills | [[project-kickoff-prd]] · [[technical-specification]] · [[architecture-decision-record]] · [[implementation-plan]] · [[independent-verification]] · [[git-workflow]] |
Role
You are a disciplined engineering lead responsible for maintaining the project's living status tracker. This document is the bridge between sessions — it is what makes agentic coding sustainable across days, weeks, and months.
When to Create
Create docs/status.md as soon as the first implementation task begins. It lives alongside the implementation plan and is referenced from AGENTS.md (the documentation chain table) — every tool's pointer file leads there.
Session Protocol
At the Start of Every Session
- Read
docs/status.mdbefore doing anything else. Understand the current phase, what was done last, and what was queued for this session. - Check the In-Flight Checkpoint. If it is not
none, the previous session ended abnormally (crash, context exhaustion, interruption) — the checkpoint is your recovery point. Resume from its "next step", then note the recovery in this session's handoff entry. - Read the latest handoff log entry. This is your briefing. Follow its "next session should…" instruction unless the user redirects.
During the Session — Checkpoint Cadence
Long sessions must not hold progress only in the context window. Write intermediate state at task granularity — not every step (wasteful), not only at session end (catastrophic on failure):
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 · 171 lines · 98 tokens per session scan A 9cd20a8f0ccd
status-tracker is a skill published in the GitHub repository affectionatec/agentic-engineering (4 stars, last pushed 2mo ago), licensed MIT. It adds 98 tokens to every session and 2,312 once invoked, about $0.0005 per session on Opus 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.
Other skills, from other repositories
vibe-to-agentic-framework
The conceptual framework behind the presentation — what "Vibe Coding to Agentic Engineering" means, why the journey is structured the way it is, and how every slide fits the narrative arc.
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…
presentation-structure
Knowledge about the presentation slide format, weight system, navigation, and section structure.
presentation-styling
Knowledge about CSS classes, component patterns, and syntax highlighting in the presentation.
weather-fetcher
Instructions for fetching current weather temperature data for Dubai, UAE from Open-Meteo API.
time-skill
Display the current time in Pakistan Standard Time (PKT, UTC+5). Use when the user asks for the current time, Pakistan time, or PKT.