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 arcayne/agentic-delivery-playbook --skill claudegit 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/skills/arcayne/agentic-delivery-playbook/claude)<a href="https://agentmods.dev/skills/arcayne/agentic-delivery-playbook/claude"><img src="https://agentmods.dev/badge/skills/arcayne/agentic-delivery-playbook/claude/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/skills/arcayne/agentic-delivery-playbook/claude"><img src="https://agentmods.dev/badge/skills/arcayne/agentic-delivery-playbook/claude.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 | $0.00070 | $0.00593 |
| Opus 5 | $0.00035 | $0.00296 |
| Sonnet 5 | $0.00014 | $0.00119 |
| Haiku 4.5 | $0.00007 | $0.00059 |
Grade A, and why
agentic-delivery-playbook 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 8d 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
Agentic Delivery Playbook
Classify the task before editing:
- Direct: clear, low-risk, one or two files, obvious validation. Do not create run artifacts; edit narrowly, validate, and report evidence.
- Lightweight: bounded low/medium-risk work that needs a compact contract. Create minimal run artifacts and stop for approval before implementation unless the user asked for end-to-end work.
- Full: broad, ambiguous, sensitive, provider/config/state/API/routing/public-contract, cross-package, or drift-prone work. Use the full spec, critique, approval, implementation, QA, fix/escalation, and closeout workflow.
For lightweight or full mode, read workflow.md in this skill folder and follow it as the operating procedure.
Always:
- Use the least intrusive process that can safely produce evidence.
- Do not implement non-direct work before spec approval unless the user explicitly asks for an uninterrupted end-to-end run.
- Implement only against the approved spec.
- QA the diff against the spec, not against the implementer summary.
- Close out with changed files, validation commands/results, known gaps, and next action.
- Do not invent evidence or claim model-specific routing unless it was actually controlled and recorded.
- For Full mode, do not silently continue on default model routing. If no project route config or explicit user-selected route exists, stop before coding and ask the user to create route overrides, switch/select a model manually, approve a default-route exception, or narrow/split the task.
- For broad Full-mode work, choose a recursive decomposition strategy before implementation: root planning stays coarse, launched workers get bounded slice contracts, and deeper planners own local subtree maps. Do not use one giant whole-PRD worker except as a recorded exception.
If model routing, subagents, reasoning controls, or review tools are unavailable, record runtime-default and avoid model-specific claims. For Full mode, unavailable routing is a blocker until the user approves a default-route exception or the task is narrowed.
Full-mode route rules:
- Missing model config is not approval to target
agent-defaultorruntime-default. - Record Full-mode missing config as
pending-user-decisionuntil resolved. - If the user approves defaults, record
exception-approvedwith reason and evidence. - If a worker/reviewer times out or returns unusable output, mark that gate failed. Parent takeover is allowed only as an explicit exception; do not mark the timed-out gate as passed.
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.
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.
- 8d ago First seen · 35 lines · 0 tokens per session scan A 34a5e8a45068
agentic-delivery-playbook is a skill published in the GitHub repository arcayne/agentic-delivery-playbook (10 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 593 once invoked, about $0.0003 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
beautify-with-pingfusi
Beautify or redesign an existing website through iterative pingfusi review rounds with a real human reviewer. Use when asked to "beautify this website," "make this page look professional," "polish this UI/design," "improve the visual design," or finish an AI-built page when there is no reference site to match. Do not…
review-video-with-pingfusi
Have any video reviewed by a real human, through iterative pingfusi review rounds. Use when asked to "review this video", "check the rendered video", "does this video match the prompt/brief", "what do people think of this ad/trailer/demo", or after rendering a Remotion composition or AI-generated clip that no test can…
fix-with-pingfusi
Fix or polish an existing website clone/draft using pingfusi review rounds. Use when the user says "fix it with pingfusi", "polish this clone", "make this match the original", or asks to finish/verify a draft built by any tool (ditto, lovable, v0, hand-written) until the review passes.
pixel-perfect-clone
Clone, copy, or replicate a website/page pixel-perfect using pingfusi. Use when the user asks to clone a site or page with pingfusi, copy a webpage's design, replicate a page, or make a pixel-perfect copy of a URL. Drives the full enforced pipeline - capture, numeric gates, behavior reproduction, and review rounds…
pingfusi-review
Use Pingfusi proactively whenever a coding agent reaches a question it cannot settle with code, automated tests, documentation or search, or a local browser and needs real human judgment or real-world verification. Trigger even when the user does not mention Pingfusi for subjective choices about copy, design, clarity…
owasp-reviewer-prompt
A paranoid OWASP-Top-10-aware system prompt for AI code review that traces data flow, treats every input as malicious, maps each finding to an OWASP category, and outputs a structured Summary / Findings / Severity / Score block reviewers can act on.