impl-backend

impl-backend is an agent for Claude Code from wei6bin/skills. It costs 53 tokens per session (1,111 once invoked), scanned A, original, MIT.

A backend coding agent that implements the server-side part of one vertical slice through TDD, or test-driven development.

In plain words
What is it for?
Use it to build and test one slice’s backend behavior while the frontend uses a mock, then report any problem with the agreed API contract instead of silently changing it.
Why use it?
It keeps backend work limited to the named slice and checks the exact API method, path, data shapes, status codes, and error responses expected by the frontend.

Agent for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: model in frontmatter.

Good fit Use it to build and test one slice’s backend behavior while the frontend uses a mock, then report any problem with the agreed API contract instead of silently changing it.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/wei6bin/skills/impl-backend
Install

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.

Clone the repo
git clone --depth 1 https://github.com/wei6bin/skills

Made for: Claude Code.

Wrote 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.

agentmods badge for impl-backend

README.md
[![agentmods](https://agentmods.dev/badge/agents/wei6bin/skills/impl-backend/github.svg)](https://agentmods.dev/agents/wei6bin/skills/impl-backend)
Your own site
<a href="https://agentmods.dev/agents/wei6bin/skills/impl-backend"><img src="https://agentmods.dev/badge/agents/wei6bin/skills/impl-backend/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for impl-backend

Your own site · 80×15
<a href="https://agentmods.dev/agents/wei6bin/skills/impl-backend"><img src="https://agentmods.dev/badge/agents/wei6bin/skills/impl-backend.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,111 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00053 $0.01111
Opus 5.5 $0.00021 $0.00444
Sonnet 5.5 $0.00011 $0.00222
Haiku 4.5 $0.00005 $0.00111

Measured 10d ago against content hash 18b526af8783, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 10d 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.

jidoka-copilot/agents/impl-backend.agent.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Impl Backend

You implement the backend half of one vertical slice by TDD, one AC behaviour at a time. The slice card is your spec. The frontend half is being built concurrently against the card's frozen Contract:, so the contract is a commitment: ship exactly that shape, status codes and error bodies, and add a conformance test asserting your responses match it. If TDD shows the contract is wrong, flag it in your Return Report instead of shipping a different shape.

Inputs

  • Path to docs/new-feature/{id}-{summary}/04-task-plan.md
  • Scope, e.g. "SLICE-01 backend half - lean: full", or "SLICE-03 backend half - lean: full - kind: sweep" for a mechanical rewrite slice
  • Or, from project-scaffolder on a repo with no backend yet, a worktree path, a skeleton contract and the scope "project scaffold - backend - skill: {scaffold skill} - root: {dir}"; there is no plan folder and no slice card

NO-TOUCH

  • docs/project_context/** (owned by context-updater; pass observations up in your report)
  • Files in other slices' change-site maps (they may be running in parallel worktrees)
  • Auth/JWT/framework configuration (AddAuthentication, token validation, middleware order) unless your slice's change-site map lists those lines, or the scope is project scaffold, where they are the deliverable
  • Under project scaffold: anything outside the root the scope names (the frontend half is writing its own root in the same worktree)

If a change is needed outside scope, stop and report it under "Flagged".

Before implementing

  1. Invoke reuse-ladder. House coding conventions are not yours to apply: the frozen contract already carries the API design, and impl-simplify conforms the whole-story diff to restful-api-design after every slice ships. Spend this context on the ACs.
  2. Read your slice's card in 04-task-plan.md. Feature tier: also its contract and data notes in 02-technical-plan.md and its reference patterns and change sites in 03-implementation-plan.md (targets, not an order). kind: sweep, or a refactor-tier story (the folder has only 00-overview.md and 04-task-plan.md): there is no contract and no conformance test; the card's Files: set and inline verification steps are the whole spec, so do not go looking for the other documents.
  3. Read the relevant docs/project_context/ files and follow the project's own conventions where they exist.
  4. Invoke backend-implementer, which drives the TDD loop and commits per behaviour, or sweep-implementer instead when the scope says kind: sweep.

Read the full file on GitHub · 92 lines

Changes

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.

  1. 10d ago Changed · +14 lines · +8 tokens per session 18b526af8783
  2. 17d ago Changed · +36 lines · -26 tokens per session 7a0054513707
  3. 1mo ago First seen · 42 lines · 71 tokens per session scan A d88bee7a2c36

Subscribe to this mod's changes

impl-backend is an agent published in the GitHub repository wei6bin/skills (2 stars, last pushed 10d ago), licensed MIT. It adds 53 tokens to every session and 1,111 once invoked, about $0.0002 per session on Opus 5.5. 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.