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/fattain-naime/engineering-docs/project-plannpx skills add fattain-naime/engineering-docs --skill project-plangit clone --depth 1 https://github.com/fattain-naime/engineering-docsWhat 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 | $0.00068 | $0.04657 |
| Opus 5 | $0.00034 | $0.02329 |
| Sonnet 5 | $0.00014 | $0.00931 |
| Haiku 4.5 | $0.00007 | $0.00466 |
Grade A, and why
project-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 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 — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Produce a project plan that defines scope, milestones, timeline, ownership, dependencies, budget, quality standards, and risk at the delivery level - the document that answers "what are we building, in what order, who owns each part, and by when" for anyone tracking the project, not just the engineers building it.
This is not a technical design document. It does not specify how any single component works - it specifies the shape and sequence of the overall effort so that individual technical-blueprint and implementation-plan documents have a timeline and ownership structure to slot into.
Input
Works best with: The name of the project and a description of its overall goal and scope. Also valuable: Team size and roles, hard deadlines or launch dates, budget constraints, known dependencies on other teams or vendors, prior similar projects and how long they took.
Example invocation: Create a project plan for building a subscription-billing SaaS product from scratch. Team of 3 engineers, 1 designer, 1 PM. Target: usable beta in 3 months. No hard external deadline but investors expect a demo by month 4.
Key Concepts
Work Breakdown Structure (WBS)
Decompose the project into progressively smaller deliverables until each leaf item is small enough to estimate confidently (typically 1 day - 2 weeks of work). A WBS is a tree, not a flat list: Project -> Phases -> Workstreams -> Deliverables -> Tasks.
Estimation Methodology
Use a structured estimation approach rather than gut-feel guesses. The recommended methods, in order of preference:
- Three-point estimation -- For each deliverable, estimate three values:
- Optimistic (O): Best-case scenario, everything goes right
- Most likely (M): Realistic estimate under normal conditions
- Pessimistic (P): Worst-case scenario, significant obstacles
- Expected duration: E = (O + 4M + P) / 6
- Standard deviation: SD = (P - O) / 6
- This produces a probability-weighted estimate and exposes estimate uncertainty.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 327 lines · 68 tokens per session scan A 76614099763f
project-plan is a skill published in the GitHub repository fattain-naime/engineering-docs (4 stars, last pushed 17d ago), licensed MIT. It adds 68 tokens to every session and 4,657 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.