be-framework-coding-standard

A set of implementation rules for backend applications written with a declared framework, such as Express, NestJS, FastAPI, or Java frameworks.

In plain words
What is it for?
Use it to build or review APIs, backend-for-frontend services, microservices, workers, jobs, and integrations after the project’s backend technology is defined.
Why use it?
It keeps new backend code aligned with the project’s chosen framework, API contracts, file layout, configuration, error handling, logging, and tests.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/evolplus/talos/be-framework-coding-standard
Any agent
npx skills add evolplus/talos --skill be-framework-coding-standard
Clone the repo
git clone --depth 1 https://github.com/evolplus/talos

Made for: Claude Code, Codex.

Per session 163 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,576 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00163 $0.02576
Opus 5 $0.00081 $0.01288
Sonnet 5 $0.00033 $0.00515
Haiku 4.5 $0.00016 $0.00258

Measured 2d ago against content hash 62765e44437e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

be-framework-coding-standard 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.

skills/be-framework-coding-standard/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BE Framework Coding Standard

When to use

You are BE Dev implementing or reviewing backend code after the backend track and stack are declared in the signed-off SRS. This skill standardizes backend implementation without turning a feature task into a framework migration.

Inputs and outputs

  • Inputs: task assignment, docs/SRS.md headers Backend-Track: and Backend-Framework:, SRS §3.4.4 API Contract Format, SRS §3.4.5 Source Layout, SRS §3.4.6 Environment Configuration, task US / FR / NFR IDs, architecture, data-contract constraints, external-integration specs, current backend source tree, manifests, and installed framework versions.
  • Outputs: backend code under the declared backend source root, framework-native handlers/controllers/services/repositories/workers, API contracts when endpoints/messages change, validation/error/observability behavior aligned to SRS/architecture, and focused unit/integration/contract tests.

Backend track selection

Backend-Track: declares the service role:

Value Meaning
backend-web Web-facing backend: public/internal HTTP API, BFF, web gateway, session-backed web API, or API directly serving frontend clients.
backend-service Microservice/runtime service: domain service, worker, consumer, scheduler, service-mesh API, gRPC service, event processor, or internal integration service.
multiple More than one backend row exists; select per §3.4.5 Source Layout / architecture container.
N/A No backend implementation applies.

Framework selection

  1. Read docs/SRS.md before inspecting manifests. Headers Backend-Track: and Backend-Framework: are authoritative.
  2. If Backend-Framework: is one supported value, select that framework reference.
  3. If Backend-Framework: is multiple, select the framework from the §3.4.5 backend row that owns the task's service/container/path. If no row matches or several rows match, halt with NEEDS_CONTEXT and cite the candidate rows.
  4. If Backend-Track: is multiple, select the track from the same §3.4.5 backend row. If one framework spans both tracks, the track still controls lifecycle expectations.
  5. If either header is N/A, do not perform BE implementation; report that no backend applies.
  6. If either header is missing, TBD, unsupported, or inconsistent with §3.4.5, halt and return the work to BA:
    • greenfield/authored SRS: BA Phase 1.X must ask the user to choose;
    • brownfield/extracted SRS: BA Mode E must detect from source evidence and write the SRS fields.
  7. After selecting the reference, inspect manifests/source only as a consistency check. If code evidence contradicts the SRS-selected track/framework, halt and raise an open issue; do not silently switch references.

Read the full file on GitHub · 131 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. 2d ago First seen · 131 lines · 163 tokens per session scan A 62765e44437e

Subscribe to this mod's changes

be-framework-coding-standard is a skill published in the GitHub repository evolplus/talos (8 stars, last pushed 28d ago), licensed Apache-2.0. It adds 163 tokens to every session and 2,576 once invoked, about $0.0008 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

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…

openai/codex · 113 tokens

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…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens