engifoundry-deliver

engifoundry-deliver is a skill for Claude Code from caoyuan-fire/engi-foundry-skill. It costs 38 tokens per session (613 once invoked), scanned A, original, Apache-2.0.

A delivery workflow for EngiFoundry work packages after their implementation has passed verification. It reads the recorded evidence, handles required approval, and closes the delivery or records it for rework.

In plain words
What is it for?
Use it to process verified work packages, obtain user or automatic acceptance when required, close accepted deliveries, or record implementation and contract rejections.
Why use it?
It keeps delivery decisions tied to verification results and records whether work was accepted or needs changes. It also prevents unverified or blocked work from entering the delivery stage.

Skill for Claude Code

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

Part of the engifoundry-bundle plugin — 10 skills, 1 hook, 1 MCP server shipped together

Good fit Use it to process verified work packages, obtain user or automatic acceptance when required, close accepted deliveries, or record implementation and contract rejections.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/caoyuan-fire/engi-foundry-skill/engifoundry-deliver
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 caoyuan-fire/engi-foundry-skill --skill engifoundry-deliver
Clone the repo
git clone --depth 1 https://github.com/caoyuan-fire/engi-foundry-skill

Made for: Claude Code.

Or install engifoundry-bundle, the plugin that ships this one along with the rest of its 10 skills, 1 hook, 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 engifoundry-deliver

README.md
[![agentmods](https://agentmods.dev/badge/skills/caoyuan-fire/engi-foundry-skill/engifoundry-deliver/github.svg)](https://agentmods.dev/skills/caoyuan-fire/engi-foundry-skill/engifoundry-deliver)
Your own site
<a href="https://agentmods.dev/skills/caoyuan-fire/engi-foundry-skill/engifoundry-deliver"><img src="https://agentmods.dev/badge/skills/caoyuan-fire/engi-foundry-skill/engifoundry-deliver/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 engifoundry-deliver

Your own site · 80×15
<a href="https://agentmods.dev/skills/caoyuan-fire/engi-foundry-skill/engifoundry-deliver"><img src="https://agentmods.dev/badge/skills/caoyuan-fire/engi-foundry-skill/engifoundry-deliver.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 613 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 $0.00038 $0.00613
Opus 5 $0.00019 $0.00307
Sonnet 5 $0.00008 $0.00123
Haiku 4.5 $0.00004 $0.00061

Measured 11d ago against content hash 73c3c81cf0d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

engifoundry-deliver 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 11d 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/engifoundry-deliver/SKILL.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

EngiFoundry Deliver

Read ./engifoundry.config.json, the project-owned workspace guide, Workflow config, and contracts.md. Then read the PAK, its execution.verificationRef, the referenced Verify record, required artifacts, and closeout requirements.

Boundary

The Agent reads this contract only for a PAK whose latest verification result is verified-available and whose execution status is verified-available or acceptance-pending. extension-required, rejected, or blocked cannot enter Deliver. Verification evidence is input; during this work the Agent does not repeat Verify or Review, implement rework, or revise contracts.

Acceptance

The acceptance record and Package state describe exactly one current fact:

  1. full-auto supplies auto-accepted when current verification is verified-available.
  2. job-approval and package-approval are acceptance-pending until the user decides on the concise Verify result.
  3. User approval supplies user-approved.
  4. An actionable implementation rejection is rework-required with kind implementation.
  5. A changed goal or contract is rework-required with kind contract.
  6. A rejection without an actionable fact remains acceptance-pending and requires the reason.

Every rework-required acceptance fact has an immutable rejection record attached as execution.deliveryRef. Implementation rejection means the affected Jobs and Package execution are also rework-required; contract rejection means Package planning is also rework-required.

Closeout

Confirm every required artifact is referenced and every closeout requirement is satisfied. Create only delivery outputs required by the PAK. Satisfied acceptance and closeout facts are recorded in one immutable delivery JSON, attached as execution.deliveryRef, with execution.status: completed.

Every completed PAK also has the matching human-readable DELIVERY-<NNN>.md defined by the reference contract. It summarizes PAK execution, current engineering state, evidence and artifacts, severity-labeled risks, and handoff facts. This summary is required even when no additional user-facing document was requested.

Read the full file on GitHub · 43 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 43 lines · 38 tokens per session scan A 73c3c81cf0d7

Subscribe to this mod's changes

engifoundry-deliver is a skill published in the GitHub repository caoyuan-fire/engi-foundry-skill (2 stars, last pushed 17d ago), licensed Apache-2.0. It adds 38 tokens to every session and 613 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.