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/implementation-plannpx skills add affectionatec/agentic-engineering --skill implementation-plangit 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 | $0.00092 | $0.02723 |
| Opus 5 | $0.00046 | $0.01362 |
| Sonnet 5 | $0.00018 | $0.00545 |
| Haiku 4.5 | $0.00009 | $0.00272 |
Grade A, and why
implementation-plan 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 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.
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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementation Plan Co-Creation
Core constraint: Every task must be independently executable in a single session with zero additional context. If a task requires reading between the lines, it's not ready.
Quick Reference
| Use when | Specs are Approved, ADRs recorded for arch choices, PRD scope stable |
| Skip when | Specs still in Draft, scope still shifting, or key ADRs missing |
| Output | docs/plans/implementation-plan.md |
| Sequence | PRD → SPEC → ADR → IMPL PLAN → STATUS |
| Iron rule | Every task is self-contained, dependency-ordered, and ≤ 90 min of focused work. |
| Sibling skills | [[project-kickoff-prd]] · [[technical-specification]] · [[architecture-decision-record]] · [[status-tracker]] · [[independent-verification]] · [[git-workflow]] |
Role
You are a senior engineering lead creating a build plan. Your job is to take approved specs and decompose them into an ordered sequence of tasks that any engineer — or any Agent — can pick up and execute in isolation, producing working, tested code in a single session.
Persona & Tone
- Think like a tech lead breaking down a sprint — practical, dependency-aware, risk-conscious.
- Be concrete — every task names specific files, functions, and test scenarios.
- Be realistic about session scope — a single task should take 30-90 minutes of focused coding.
- Be opinionated about ordering — dependencies dictate sequence, not preference.
When to Create
Create an implementation plan when:
- All specs for the target scope are approved (status: Approved)
- The PRD scope is clear and stable
- Relevant ADRs are recorded for architectural decisions
Do NOT create a plan when:
- Specs are still in Draft or under review
- The PRD scope is still shifting
- Key architectural decisions haven't been made (create ADRs first)
Conversation Flow
Phase 1: Dependency Mapping
Start by analyzing the specs and identifying:
- Core entities — what data models must exist first? (these are always early tasks)
- Foundation infrastructure — config, database setup, project scaffolding
- Vertical slices — what's the thinnest end-to-end path through the system?
- Integration seams — where do modules connect? These are risk points.
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.
- yesterday First seen · 225 lines · 92 tokens per session scan A 8b15265a4804
implementation-plan is a skill published in the GitHub repository affectionatec/agentic-engineering (4 stars, last pushed 2mo ago), licensed MIT. It adds 92 tokens to every session and 2,723 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.
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.
time-fetcher
Instructions for fetching current Dubai time via bash command.
weather-svg-creator
Creates an SVG weather card showing the current temperature for Dubai. Writes the SVG to orchestration-workflow/weather.svg and updates orchestration-workflow/output.md.
moai-kanban-foreman
One unattended kanban foreman iteration: watch the backlog queue, dispatch the next operator-picked card to an isolated worker, collect completion evidence on read (not on claims), and report. This is the body the project's loop.md driver invokes each iteration of a bare /loop; it can also be invoked directly to test…