persistent-delivery

persistent-delivery is a skill for Claude Code, Codex from ytunahankskn/oh-meine-excode. It costs 29 tokens per session (272 once invoked), scanned A, original, MIT.

A work method for coding agents that keeps checking and improving a task until defined acceptance checks pass.

In plain words
What is it for?
Use it for tasks that must be completed end to end, such as making tests pass, fixing type errors, completing a build, or matching a requested interface.
Why use it?
It reduces the risk of stopping with unfinished work or claiming success without fresh evidence. Failed fixes are retried within set limits.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Good fit Use it for tasks that must be completed end to end, such as making tests pass, fixing type errors, completing a build, or matching a requested interface.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ytunahankskn/oh-meine-excode/persistent-delivery
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 ytunahankskn/oh-meine-excode --skill persistent-delivery
Clone the repo
git clone --depth 1 https://github.com/ytunahankskn/oh-meine-excode

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 persistent-delivery

README.md
[![agentmods](https://agentmods.dev/badge/skills/ytunahankskn/oh-meine-excode/persistent-delivery.svg)](https://agentmods.dev/skills/ytunahankskn/oh-meine-excode/persistent-delivery)
Your own site
<a href="https://agentmods.dev/skills/ytunahankskn/oh-meine-excode/persistent-delivery"><img src="https://agentmods.dev/badge/skills/ytunahankskn/oh-meine-excode/persistent-delivery.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 272 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 $0.00029 $0.00272
Opus 5 $0.00015 $0.00136
Sonnet 5 $0.00006 $0.00054
Haiku 4.5 $0.00003 $0.00027

Measured 7d ago against content hash fa49d8ecf18a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

persistent-delivery 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 7d 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.

plugins/oh-meine-excode/skills/persistent-delivery/SKILL.md · 45 lines

What it actually says

Persistent Delivery

Use this skill when the user wants persistence: "finish it", "don't stop halfway", "keep going until it passes".

This is the Codex-friendly counterpart to a completion loop.

Loop

Repeat:

  1. choose the next incomplete acceptance target
  2. implement or delegate a bounded fix
  3. verify with fresh evidence
  4. mark the target complete only if checks actually pass

Acceptance Tracking

Before or during work, define a compact checklist of acceptance targets.

Examples:

  • UI renders and matches the requested layout
  • tests for the changed behavior pass
  • build succeeds
  • no type errors remain in touched code

Do not declare success on intuition. Use fresh evidence.

Retry Policy

  • If a fix fails, revise the approach and try again.
  • If the same issue repeats several times, surface it as a likely fundamental blocker.
  • If verification is impossible in the environment, say exactly what could not be verified.

Delegation Guidance

  • Delegate only bounded fixes or review passes.
  • Keep acceptance tracking and final sign-off in the main thread.
  • Use a second-pass agent when the change is risky or spans many files.
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. 7d ago First seen · 45 lines · 29 tokens per session scan A fa49d8ecf18a

Subscribe to this mod's changes

persistent-delivery is a skill published in the GitHub repository ytunahankskn/oh-meine-excode (2 stars, last pushed 5mo ago), licensed MIT. It adds 29 tokens to every session and 272 once invoked, about $0.0001 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