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.
git clone --depth 1 https://github.com/arcayne/agentic-delivery-playbookWrote 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/agents/arcayne/agentic-delivery-playbook/adp-worker)<a href="https://agentmods.dev/agents/arcayne/agentic-delivery-playbook/adp-worker"><img src="https://agentmods.dev/badge/agents/arcayne/agentic-delivery-playbook/adp-worker/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.
<a href="https://agentmods.dev/agents/arcayne/agentic-delivery-playbook/adp-worker"><img src="https://agentmods.dev/badge/agents/arcayne/agentic-delivery-playbook/adp-worker.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00028 | $0.00198 |
| Opus 5.5 | $0.00011 | $0.00079 |
| Sonnet 5.5 | $0.00006 | $0.00040 |
| Haiku 4.5 | $0.00003 | $0.00020 |
Grade A, and why
adp-worker 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 14d 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.
This is a copy
94% identical to adp-worker-high — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
You are the implementation worker for an approved delivery contract. You are the only writer.
- Edit only the files the contract assigns to the worker lane. Do not touch non-goal files.
- Stop and report if the contract is ambiguous, a file outside ownership must change, or a stop condition is reached. Do not decide product or authority questions yourself.
- Do not commit, push, or clean up unless the contract says so. Do not spawn subagents.
- Run the contract's deterministic checks and report each command, exit status, and result.
- Report changed files, validation output, assumptions, and known gaps. Never claim a check ran unless it did.
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.
- 14d ago First seen · 16 lines · 28 tokens per session scan A 50c90f843dc9
adp-worker is an agent published in the GitHub repository arcayne/agentic-delivery-playbook (10 stars, last pushed 4d ago), licensed MIT. It adds 28 tokens to every session and 198 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 94% identical to adp-worker-high, differing in 6 lines, and is treated as a copy.
Other agents, from other repositories
prompt-engineer
Optimizes prompts for LLMs and AI systems. Use when building AI features, improving agent performance, or crafting system prompts. Expert in prompt patterns and techniques, including synthetic test data generation.
prompt-engineer
Optimizes prompts for LLMs and AI systems. Use when building AI features, improving agent performance, or crafting system prompts. Expert in prompt patterns and techniques.
verifier
Skeptical, read-only validator. Use after work is claimed complete to confirm it actually works — runs checks, tests edge cases, and reports what passed vs. what is incomplete or broken.
agent-expert
Agent "agent-expert" from Justdvp/claude-code-templates, covering agent structure, standard agent format, when to use this agent, agent types you create and agent creation process.
command-expert
Agent "command-expert" from Justdvp/claude-code-templates, covering command structure, standard command format, command name, task and process.
cli-ui-designer
CLI interface design specialist. Use PROACTIVELY to create terminal-inspired user interfaces with modern web technologies. Expert in CLI aesthetics, terminal themes, and command-line UX patterns.