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/pangon/ai-sdlc-framework/sdlc-implementation-plannpx skills add pangon/ai-sdlc-framework --skill sdlc-implementation-plangit clone --depth 1 https://github.com/pangon/ai-sdlc-frameworkWrote 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/skills/pangon/ai-sdlc-framework/sdlc-implementation-plan)<a href="https://agentmods.dev/skills/pangon/ai-sdlc-framework/sdlc-implementation-plan"><img src="https://agentmods.dev/badge/skills/pangon/ai-sdlc-framework/sdlc-implementation-plan.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 | $0.00049 | $0.03384 |
| Opus 5 | $0.00024 | $0.01692 |
| Sonnet 5 | $0.00010 | $0.00677 |
| Haiku 4.5 | $0.00005 | $0.00338 |
Grade A, and why
SDLC-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 5d 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 — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructions
You are working in the Code phase. You are creating an implementation plan — a phased sequence of short development tasks that, when executed in order, build the project incrementally from nothing to full feature set. Each phase ends with a system that can be deployed or at least tested end-to-end, even if not feature-complete.
The plan populates 3-code/tasks.md with tasks and an Execution Plan that groups them into ordered phases.
Phase Validation
Before doing anything else, read the **Phase**: field of the ### Current State subsection in CLAUDE.md. Then follow the matching case below:
-
Not initialized— Stop, recommend/SDLC-init, and do not proceed. -
Specification— Stop, recommend/SDLC-elicitto continue refining specifications or/SDLC-designto start the design phase, and do not proceed. -
Design— components have not been identified yet. Stop, recommend/SDLC-decomposefirst, and do not proceed. -
Codewith no tasks yet (3-code/tasks.mdcontains only the template) — this is the expected entry point. Evaluate prerequisites:- (a) All design documents are drafted and components are identified — re-verify the two corresponding Design → Code preconditions via the "How to verify" column of the Phase Gates table in
CLAUDE.md(the gate was already crossed, but the state may have drifted) - (b)
3-code/tasks.mdhas no tasks yet (only the template)
Then:
- If (a) is not met — Stop, explain what is missing.
- If (b) is not met (tasks already exist) — Warn that running this skill will replace the pending task entries (
Todo/Blocked) and the current/future phases of the Execution Plan; completed work is preserved (see Re-planning in Workflow step 2). Proceed only on explicit user confirmation. - If all met — proceed with Setup.
- (a) All design documents are drafted and components are identified — re-verify the two corresponding Design → Code preconditions via the "How to verify" column of the Phase Gates table in
-
Codewith tasks already in progress or done — Warn strongly that re-planning may invalidate in-progress work; completed tasks are preserved (see Re-planning in Workflow step 2). Proceed only on explicit user confirmation.
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.
- 5d ago First seen · 239 lines · 49 tokens per session scan A 38f191ca7f89
SDLC-implementation-plan is a skill published in the GitHub repository pangon/ai-sdlc-framework (125 stars, last pushed 12d ago), licensed Apache-2.0. It adds 49 tokens to every session and 3,384 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…