id-implement

A branch-based procedure for writing or editing infrastructure-as-code files for an approved change. Infrastructure as code means configuration files that describe systems such as cloud resources and Kubernetes deployments.

In plain words
What is it for?
Use it to create or update OpenTofu and Kubernetes files according to project conventions and record what was authored.
Why use it?
It keeps edits separate from the main branch and aligned with the approved list of intended changes, without applying them to live systems.

Skill for Claude CodeCodex

Part of the foundry plugin — 47 skills, 8 agents, 8 hooks, 1 MCP server shipped together

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/lukasrepublic/agentic-foundry/id-implement
Any agent
npx skills add lukasrepublic/agentic-foundry --skill id-implement
Clone the repo
git clone --depth 1 https://github.com/lukasrepublic/agentic-foundry

Made for: Claude Code, Codex.

Or install foundry, the plugin that ships this one along with the rest of its 47 skills, 8 agents, 8 hooks, 1 MCP server.

Per session 264 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,669 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 $0.00264 $0.02669
Opus 5 $0.00132 $0.01334
Sonnet 5 $0.00053 $0.00534
Haiku 4.5 $0.00026 $0.00267

Measured 2d ago against content hash be995c3bc6d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

id-implement 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/id-implement/SKILL.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

id-implement — author the IaC for the intended change on a branch (infra-delivery step 5)

The infra-delivery step sequence (a documented procedure this skill family forms — no workflow engine or state-machine file ships) drives an infra change → merge. Step 5 is the change-authoring step. After the contract is frozen at authorize, this is where the generic agent authors/edits the IaC for the intended change — scaffold/edit the OpenTofu/Kubernetes files to the handbook conventions — on a branch. It is a PROCEDURE skill the generic agent runs. It runs NO plan and mutates NOTHING — it writes files. The authored IaC is branch-quarantined (it never touches main, and it never applys or otherwise mutates live cloud state), and it NAMES the frozen intended-change manifest (the tofu-plan checkpoint's operator-frozen intended set in the acceptance-contract) it must keep the edit in sync with — so the downstream read-only id-plan plan can attribute the change for the operator/reviewer at the merge floor.

ADVISORY — not a gate, no machine-adjudicated GREEN claim

This skill is ADVISORY. It authors files + records an authoring observation; it does NOT gate, approve, or block any merge, and it does NOT decide its own PASS. The bound is the operator-frozen contract, not this skill — id-implement keeps the authored change in sync with the frozen intended set so the downstream id-plan output lets a human attribute the change. Honest disclosure: earlier design intent had a plan ≡ intended verdict computed by derive_infra_walk_verdict over the FROZEN contract at a dedicated merge gate — that machinery was retired and does not exist today. The authoring observation it records carries no machine-adjudicated GREEN claim and is NOT a verdict input. The both-modes floor is unchanged: front-authorization, the merge floor (the adopter's branch protection + CI checks — see docs/merge-floor.md) remains the merge authority, security review, and typed contracts. Running id-implement makes the operator confident the IaC realizes the frozen intended set — it is craft guidance FOR the trusted operator, not a defense against them.

Read the full file on GitHub · 135 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 · 135 lines · 264 tokens per session scan A be995c3bc6d4

Subscribe to this mod's changes

id-implement is a skill published in the GitHub repository lukasrepublic/agentic-foundry (1 stars, last pushed 2d ago), licensed MIT. It adds 264 tokens to every session and 2,669 once invoked, about $0.0013 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