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 fabricepayet/skills --skill delivery-ticketsgit clone --depth 1 https://github.com/fabricepayet/skillsWrote 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/fabricepayet/skills/delivery-tickets)<a href="https://agentmods.dev/skills/fabricepayet/skills/delivery-tickets"><img src="https://agentmods.dev/badge/skills/fabricepayet/skills/delivery-tickets/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/fabricepayet/skills/delivery-tickets"><img src="https://agentmods.dev/badge/skills/fabricepayet/skills/delivery-tickets.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 | $0.01062 |
| Opus 5 | $0.00014 | $0.00531 |
| Sonnet 5 | $0.00006 | $0.00212 |
| Haiku 4.5 | $0.00003 | $0.00106 |
Grade A, and why
delivery-tickets 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.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delivery Tickets
Purpose
Publish a dependency graph of tracer-bullet vertical slices. Each delivery ticket makes one narrow, complete behavior independently demonstrable or verifiable while preserving traceability to approved product and technical decisions.
Tracker resolution
Before reading or mutating tracked artifacts, resolve the project tracker in this order:
- an explicit instruction from the user for the current work;
- the repository's root
CONTRIBUTING.mdand any contribution document it explicitly delegates to; - the repository's root
README.md.
A tracker is configured only when the selected source explicitly designates it for product or issue tracking. A Git host, remote URL, installed connector, badge, or incidental tracker link is not enough. When the selected source names multiple trackers without routing this work, or none of the sources configures one, ask one focused question before publishing. Follow the documented project, issue type, hierarchy, labels, and workflow states when they exist.
Input gate
Require exact references and versions for:
- one current Product Contract with status
Product Approved; - one current Technical Design with status
Technical Approvedthat names that Product Contract version.
Stop when either artifact is missing, unapproved, superseded, or mismatched. Delivery planning cannot complete product or technical design.
Workflow
- Resolve inputs. Read both complete artifacts, their revision notes, stable IDs, and tracker relationships. Read repository instructions, domain terminology, ADRs, relevant code, and prior tests when needed to size executable slices.
- Build coverage maps. Account for every Product Contract rule and acceptance criterion and every Technical Design decision. Identify independent observable outcomes rather than implementation layers.
- Detect specification gaps. Route missing observable behavior to a Product Clarification Request and
product-spec. A newly approved Product Contract version requirestechnical-specto revise the affected design before ticketing resumes. Route missing engineering decisions directly to a Technical Design revision. Block only affected work; continue drafting unrelated slices when their inputs are complete. - Draft vertical slices. Apply every vertical-slice invariant below. Give each ticket only genuine blocking edges and keep the executable frontier as wide as the design allows.
- Review the graph. Present the complete proposed breakdown before mutating the tracker. For each ticket show its outcome, covered IDs, relevant technical path, independent verification, and blockers. Ask whether granularity, coverage, and blocking edges are correct; iterate until engineering explicitly approves.
- Publish. Create tickets in dependency order in the resolved tracker so native references can be added. Make them direct children of the Product Contract and relate each to the Technical Design when the tracker supports those relationships. Use native blocking links, configured ready state, and existing labels; fall back to explicit metadata in the body.
- Report the frontier. List every published ticket whose blockers are already complete or empty. Leave both approved input artifacts unchanged.
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.
- 11d ago First seen · 88 lines · 28 tokens per session scan A 92071c385bf5
delivery-tickets is a skill published in the GitHub repository fabricepayet/skills (2 stars, last pushed 15d ago), licensed MIT. It adds 28 tokens to every session and 1,062 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
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.