decommission-gate

decommission-gate is a skill for Claude Code from lukasrepublic/agentic-foundry. It costs 185 tokens per session (1,596 once invoked), scanned A, original, MIT.

A guarded procedure for turning off old software components only after a replacement works independently and the old component is safe to remove. It rechecks these conditions at the moment of removal and records the result in an append-only ledger.

In plain words
What is it for?
Use it to plan and validate migrations from legacy components, including checks for remaining users, replacement access, soak periods, and old-side safety.
Why use it?
It prevents a past approval or manually changed status from authorizing an unsafe, irreversible shutdown.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the foundry plugin — 81 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/decommission-gate
Any agent
npx skills add lukasrepublic/agentic-foundry --skill decommission-gate
Clone the repo
git clone --depth 1 https://github.com/lukasrepublic/agentic-foundry

Made for: Claude Code.

Or install foundry, the plugin that ships this one along with the rest of its 81 skills, 8 agents, 8 hooks, 1 MCP server.

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 decommission-gate

README.md
[![agentmods](https://agentmods.dev/badge/skills/lukasrepublic/agentic-foundry/decommission-gate.svg)](https://agentmods.dev/skills/lukasrepublic/agentic-foundry/decommission-gate)
Your own site
<a href="https://agentmods.dev/skills/lukasrepublic/agentic-foundry/decommission-gate"><img src="https://agentmods.dev/badge/skills/lukasrepublic/agentic-foundry/decommission-gate.svg" alt="Measured on agentmods" height="20"></a>
Per session 185 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,596 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 5.1 $0.00185 $0.01596
Opus 5 $0.00093 $0.00798
Sonnet 5 $0.00037 $0.00319
Haiku 4.5 $0.00018 $0.00160

Measured 6d ago against content hash 7ec48d2d9247, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

decommission-gate 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 6d 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/decommission-gate/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

decommission-gate — build-and-validate first, turn-off last, GO re-derived live

Turn-off is the one irreversible, highest-blast-radius action of a migration. This skill governs it with three machine-checkable stages driven through scripts/foundry-decommission.py. The gate consumes a recorded design principle: a persisted "validated" flag alone NEVER authorizes a sever — GO is re-derived from live re-checks at the moment of turn-off.

The register (one YAML, class-aware, generated status)

  • Enumerate every in-scope component in decommission-register.yaml: stable id, the legacy_identity being turned off, the replacement and how it is reached, a class, a parallel_name, a custody flag, a soak_window, per-component checks.reverify / checks.old_safe slot commands (read-only by contract), and a generated gate_status — derived from the ledger by validate-register --regen, NEVER hand-edited (a hand edit that disagrees with the ledger fails validation closed).
  • Class semantics decide the old-side safety question (they are OPPOSITES, not variants):
    • endpoint-bearing (inbound) — safe when ZERO consumers remain over the soak window (flow logs to the old interface / load-balancer request+connection counts == 0).
    • headless (outbound worker: signer, poller, listener) — the hazard is DUAL-OPERATION (double-spend, conflicting signatures, duplicated side effects), so safe means the old instance is QUIESCED: stopped + confirmed down AND no new outbound activity.
    • decommission-only (no replacement) — zero-traffic corroboration of the dead claim, so a live component cannot be hand-downgraded to "dead" to skip the gate.

The independence policy (positive-leaning — no pass-by-omission)

  • The policy template denies on any known legacy marker AND denies any host-like endpoint ref NOT on the allow-set — a dependency reached by an un-enumerated hostname cannot pass by omission. Evaluate it over the component's EFFECTIVE rendered config (the checks.reverify slot renders — e.g. helm template output + IaC source literals — and evaluates; a render error is FATAL, never skipped):

Read the full file on GitHub · 91 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. 6d ago First seen · 91 lines · 185 tokens per session scan A 7ec48d2d9247

Subscribe to this mod's changes

decommission-gate is a skill published in the GitHub repository lukasrepublic/agentic-foundry (1 stars, last pushed yesterday), licensed MIT. It adds 185 tokens to every session and 1,596 once invoked, about $0.0009 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

spawn-reviewers

Spawn and collect the reviewer fleet at stage20spawnreviewers. Consumes spawn.json.spec (the authoritative spawn spec from derive-spawn-spec / derive-static-spec), resolves GRAPHPROJECT, builds per-agent prompts from the per-agent template + role suffixes (Bug Hunter A/B, Unified Auditor, Domain Critics, Impact…

closedloop-ai/claude-plugins · 182 tokens

verify-findings

Dispatch and collect the finding-verifier fleet at stage23verifyfindings (PLN-722). Reads verifymanifest.json (written by stage22bverifyprepare), spawns one falsify-oriented verifier Task per toverify[] entry with mode-specific Task scheduling (GitHub mode dispatches verifiers synchronously; local mode uses parallel…

closedloop-ai/claude-plugins · 171 tokens

show-me-proof

증거줘. 증거줘. 테스트 로그, 변경사항, 완료 근거를 내.

Keonho-Chu/menhera-loop · 20 tokens

ticket

Turn a note from the living manual (idea, feedback, or bug in a block, or a free-form report) into an actionable developer ticket with user stories, functional requirements, and acceptance criteria, plus open questions when completeness can't be verified. Syncs the manual's queue index and, when a tracker is…

dougstanford/living-manual · 94 tokens

agent-harness

Browse and explore agent harness frameworks and Claude Code resource collections. Use when the user wants to learn about, explore, or use agent orchestration frameworks, multi-agent architectures, or Claude Code resource catalogs — e.g., "how does Archon work?", "show me everything-claude-code resources", "find an…

berekvolgyipeter/dotclaude · 129 tokens

claude-code

Expert guidance on Claude Code configuration, capabilities, and troubleshooting. Use this skill whenever the user asks about Claude Code features, configuration, best practices, or troubleshooting — even if phrased informally. Covers MCP servers, plugins, skills, subagents, hooks, permissions, keybindings, settings…

berekvolgyipeter/dotclaude · 92 tokens