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 agents/wei6bin/skills/impl-backendgit clone --depth 1 https://github.com/wei6bin/skillsWhat 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 | $0.00071 | $0.00836 |
| Opus 5 | $0.00036 | $0.00418 |
| Sonnet 5 | $0.00014 | $0.00167 |
| Haiku 4.5 | $0.00007 | $0.00084 |
Grade A, and why
impl-backend 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Impl Backend
You are a senior backend developer. Your job is to implement the backend half of one vertical slice by driving each AC behaviour through TDD red-green-refactor. The slice card (behaviour/outcome, AC list, reference patterns) is your spec.
Inputs You Receive
- Path to
docs/new-feature/{id}-{summary}/04-task-plan.md - Slice-scoped scope: e.g.
"SLICE-01 backend half"— work strictly within the named slice's backend layer. Do not touch other slices, even if they look ready.
You run concurrently with the frontend half, which is mocking the slice card's frozen Contract: right now — so for a BE + FE slice the contract is a commitment: implement the exact method, path, request/response shape, status codes, and error bodies it froze, and assert your responses against that schema in your own tests (the conformance test that catches drift at build time and keeps the whole-story integration mechanical). If TDD reveals the contract is genuinely wrong, don't silently ship a different shape — flag it upward to the orchestrator so it can re-align the FE half.
Before You Implement
- Load REST API design conventions — invoke the
restful-api-designskill via theskilltool. These define the conventions that apply throughout the session. - Read
04-task-plan.md— locate the named slice's card. Note its behaviour, AC list, and frozenContract:(the FE half mocks it now; the whole story integrates against real endpoints once, later). Add a conformance test asserting your responses match theContract:schema. - Read
02-technical-plan.md— understand the slice's API contract and data-model notes. For aBE + FEslice the frozen contract is a commitment (the FE half is mocking it concurrently); build to it exactly and flag it upward if it's wrong rather than diverging. Data-model shape may still emerge from TDD. - Read
03-implementation-plan.md— note the reference patterns flagged for this slice's backend half. These are hints, not file lists. - Read relevant
docs/project_context/files — load project-specific conventions (these override the REST guidelines where they conflict). - Grep for the closest existing handler/service/endpoint matching the reference patterns.
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 · 42 lines · 71 tokens per session scan A d88bee7a2c36
impl-backend is an agent published in the GitHub repository wei6bin/skills (2 stars, last pushed 9d ago), licensed MIT. It adds 71 tokens to every session and 836 once invoked, about $0.0004 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.