An approval step for freezing a software feature’s acceptance contract, which defines the conditions the implementation must meet. It shows the checkpoints, gets explicit operator confirmation, and records a signed authorization.

Use it after drafting and reviewing an acceptance contract and before dispatching implementation work, or when a defect requires approval again.

It prevents implementation from starting before the specification and acceptance conditions have been reviewed and approved. It also preserves what was authorized for later checks.

authorize — Skill for Claude Code and Codex by lukasrepublic: An approval step for freezing a software feature’s acceptance…

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/authorize

Any agent

npx skills add lukasrepublic/agentic-foundry --skill authorize

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.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/lukasrepublic/agentic-foundry/authorize.svg)](https://agentmods.dev/skills/lukasrepublic/agentic-foundry/authorize)

Your own site

<a href="https://agentmods.dev/skills/lukasrepublic/agentic-foundry/authorize"><img src="https://agentmods.dev/badge/skills/lukasrepublic/agentic-foundry/authorize.svg" alt="Measured on agentmods" height="20"></a>

Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,542 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.

Model	Per session	Once invoked
Fable 5	$0.00101	$0.01542
Opus 5	$0.00051	$0.00771
Sonnet 5	$0.00020	$0.00308
Haiku 4.5	$0.00010	$0.00154

Measured 3d ago against content hash 8724faaf7e60, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

authorize 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.

skills/authorize/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/foundry:authorize

The operator-facing half of the front-authorization gate. The mechanical write is performed by ${CLAUDE_PLUGIN_ROOT}/scripts/foundry-authorize.py (validated, logged, byte-canonical). This skill is the operator-confirmation wrapper — it never re-implements the freeze logic.

When to trigger

Operator: "authorize <spec>", "/foundry:authorize <spec-or-contract>", "freeze the contract for <atom>".
After an acceptance-contract.yaml is drafted (Specify-exit, a distinct authoring phase) and BEFORE any implementation dispatch.
After a merge-time spec defect forces a re-authorization (RE-AUTH-AFTER-IMPL — pass --reauth-after-impl).

Procedure

Locate the pair. Resolve the atom's spec path and its sibling acceptance-contract.yaml (specs/features/<…>/acceptance-contract.yaml). If no contract exists, the atom is DRAFT — it must be authored first (a distinct contract-authoring phase; in dispatch mode by a separate qa-engineer worker).
Review precondition (HARDENED). Confirm the spec has cleared a review — by default, /foundry:spec-review (skills/spec-review/SKILL.md), not the retired-as-default deep adversarial-spec-audit engine (skills/audit/SKILL.md, kept dormant-invocable for an exceptional deep audit only). This script's own audit-ledger precondition (find_audit) is UNCHANGED and is the NORMAL path: it fail-closes on a spec with no matching .foundry/audit-ledger.jsonl row (spec_sha256 match + rounds >= 1 + a non-{fail,rejected, abandoned} verdict). A spec reviewed via /foundry:spec-review already has this row — skills/spec-review/SKILL.md's Phase 3 records it (foundry-audit-record.py --rounds 1 --tier single-pass-review --verdict plateau-clean) as part of the review itself, so find_audit finds it the same way it always found a deep spec audit row; no special-casing, no code change. A spec that instead ran the dormant deep audit records its ledger row the old way (see skills/audit/SKILL.md step 7). --skip-audit-reason "<reason>" stays the OPERATOR-ONLY EXCEPTION (an atom that skipped review outright, a deliberate operator override) — it is not the routine path for a spec-review-covered atom, which should already satisfy find_audit without it. Either path, do not authorize a DRAFT that cleared neither.

Read the full file on GitHub · 87 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.

3d ago First seen · 87 lines · 101 tokens per session scan A 8724faaf7e60

Subscribe to this mod's changes

authorize is a skill published in the GitHub repository lukasrepublic/agentic-foundry (1 stars, last pushed yesterday), licensed MIT. It adds 101 tokens to every session and 1,542 once invoked, about $0.0005 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.

Planning agentic-ai ai-agents anthropic claude-code claude-code-plugin developer-tools

google-ads-audit

Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…

nowork-studio/notfair-plugin · 114 tokens

review

5-pass structured code review — correctness, security, performance, readability, consistency.

SethGammon/Citadel · 17 tokens

alive:system-upgrade

Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.

alivecontext/alive · 57 tokens

codex-test-gen

Generate unit tests for specified functions using Codex MCP.

sd0xdev/sd0x-harness · 15 tokens

brand-docx

Brand-aware Word engine. Use to (1) EXTRACT a company's brand from a Word template into a reusable "Brand Profile", (2) COMPREHEND the template with the model (optional), (3) VERIFY it, (4) GENERATE new on-brand .docx documents FROM a saved profile. Trigger on "extract our brand", "learn/match this template", "use our…

ferdinandobons/brand-docs · 144 tokens

extract-resume

Parse a resume's uploaded PDF into structured JSON (basics, experience, projects, skills, education) and save it to the editor.

suxrobGM/jobpilot · 32 tokens