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.
npx skills add ytunahankskn/oh-meine-excode --skill persistent-deliverygit clone --depth 1 https://github.com/ytunahankskn/oh-meine-excodeWrote 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.
[](https://agentmods.dev/skills/ytunahankskn/oh-meine-excode/persistent-delivery)<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>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 5.1 | $0.00029 | $0.00272 |
| Opus 5 | $0.00015 | $0.00136 |
| Sonnet 5 | $0.00006 | $0.00054 |
| Haiku 4.5 | $0.00003 | $0.00027 |
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.
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:
- choose the next incomplete acceptance target
- implement or delegate a bounded fix
- verify with fresh evidence
- 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.
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.
- 7d ago First seen · 45 lines · 29 tokens per session scan A fa49d8ecf18a
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.
Other skills, from other repositories
boss-briefing
Vault health check — workflow pattern analysis, profile sync, session gap recovery, persona rule proposals.
manage-usage-sidebar
Install, check, repair, or uninstall the native Codex Usage Sidebar companion. Use when the user asks about the Codex usage header indicator, says it disappeared after a Codex update, requests repair, status, installation, or removal, or invokes @codex-usage-sidebar.
prompt-evaluator
A review workflow for prompts, agent instructions, and process specifications. It checks whether they preserve the intended task, define permissions and boundaries, route work to suitable capabilities, and provide verifiable outputs.
proof-driven
Proof-driven development. Use when implementing with formal verification using property-based testing, theorem proving, or proof tactics; zero unproven property policy enforced.
type-driven
Type-driven development. Use when developing with refined types, state machines encoded in types, or proof-carrying types; enforces totality and exhaustive pattern matching.
validation-first
Validation-first development. Use when developing with formal state machine specifications, invariants, and temporal properties before writing implementation code.