go-implementation-ownership

go-implementation-ownership is a skill for Claude Code, Codex from Dankosik/go-service-template-rest. It costs 35 tokens per session (515 once invoked), scanned A, original, MIT.

A Go code-ownership guide for deciding where accepted behavior, wiring, dependencies, generated code, and proof should live.

In plain words
What is it for?
It maps responsibilities to canonical packages and files, checks dependency direction and generated sources, identifies affected callers, and records where tests or other proof belong.
Why use it?
It prevents logic from being duplicated, placed in competing packages, or left without a clear source of truth or test location.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit It maps responsibilities to canonical packages and files, checks dependency direction and generated sources, identifies affected callers, and records where tests or other proof belong.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dankosik/go-service-template-rest/go-implementation-ownership
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.

Any agent
npx skills add Dankosik/go-service-template-rest --skill go-implementation-ownership
Clone the repo
git clone --depth 1 https://github.com/Dankosik/go-service-template-rest

Made for: Claude Code, Codex.

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 go-implementation-ownership

README.md
[![agentmods](https://agentmods.dev/badge/skills/dankosik/go-service-template-rest/go-implementation-ownership/github.svg)](https://agentmods.dev/skills/dankosik/go-service-template-rest/go-implementation-ownership)
Your own site
<a href="https://agentmods.dev/skills/dankosik/go-service-template-rest/go-implementation-ownership"><img src="https://agentmods.dev/badge/skills/dankosik/go-service-template-rest/go-implementation-ownership/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 go-implementation-ownership

Your own site · 80×15
<a href="https://agentmods.dev/skills/dankosik/go-service-template-rest/go-implementation-ownership"><img src="https://agentmods.dev/badge/skills/dankosik/go-service-template-rest/go-implementation-ownership.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 515 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 $0.00035 $0.00515
Opus 5 $0.00017 $0.00258
Sonnet 5 $0.00007 $0.00103
Haiku 4.5 $0.00003 $0.00052

Measured 3d ago against content hash 96a1cad10024, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

go-implementation-ownership 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 3d 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.

.agents/skills/go-implementation-ownership/SKILL.md · 52 lines

What it actually says

Go Implementation Ownership

Every piece of logic, wiring, and proof has one owner. Two plausible owners means placement is not decided.

responsibilities -> owner -> dependency direction -> generated/manual authority -> proof placement -> cleanup

For a delegated Decision or Review, or when the active artifact requires its result interface, load the shared specialist contract. For every changed responsibility, build OwnerRecord{responsibility, canonical_source, package, file, dependency_direction, sequence_owner, existing_proof_location_if_known, competing_paths, cleanup} from accepted behavior through callers, wiring, generated and manual sources, and cleanup. Ownerless, duplicated, or competing production paths are findings. Implementation chooses new test cases, files, and proving layers while writing code; their absence does not block the ownership decision.

The nearest record wins: read package doc.go, README.md, and seam comments before Repository Architecture, Project Structure, and Configuration Source Policy. Gates prove only what they inspect; use .golangci.yml and scripts/ci/ to subtract mechanical coverage rather than treating green as ownership evidence.

Cohesion: Group declarations that must be understood and changed together. Use package boundaries for dependency and API isolation, and files for navigable, cohesive behavior.

Caller view: Exercise each new or changed package boundary from a real caller's perspective; make inputs, results, errors, and lifecycle obligations understandable without inspecting implementation details.

Debug path: Walk a representative failure symptom through the proposed owners to the responsible rule, effect, and regression-test location. Reduce unrelated context needed to follow that path.

For a Decision, apply Project Structure's placement rules and record forced consequences for every responsibility. For Review, account for every affected owner and competing path. Complete only when implementation can proceed from a current, unambiguous map of production packages, files, sources, and dependency boundaries. This method establishes code ownership, not an approved test plan or proof level before Implementation.

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. 3d ago Changed · +2 lines 96a1cad10024
  2. 4d ago Changed · +3 lines 4f0ab3c736e9
  3. 6d ago Changed · +12 lines a5d478e61787
  4. 11d ago First seen · 35 lines · 35 tokens per session scan A c1bc0c94cb21

Subscribe to this mod's changes

go-implementation-ownership is a skill published in the GitHub repository Dankosik/go-service-template-rest (7 stars, last pushed 2d ago), licensed MIT. It adds 35 tokens to every session and 515 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 2026-08-31.