Borrowing it
Nothing to install: this file belongs to andkirby/markdown-ticket. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/andkirby/markdown-ticket/main/.agents/skills/mdt-pipeline-e2e/SKILL.mdgit clone --depth 1 https://github.com/andkirby/markdown-ticketWrote 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/andkirby/markdown-ticket/mdt-pipeline-e2e)<a href="https://agentmods.dev/skills/andkirby/markdown-ticket/mdt-pipeline-e2e"><img src="https://agentmods.dev/badge/skills/andkirby/markdown-ticket/mdt-pipeline-e2e/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/andkirby/markdown-ticket/mdt-pipeline-e2e"><img src="https://agentmods.dev/badge/skills/andkirby/markdown-ticket/mdt-pipeline-e2e.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 | $0.00080 | $0.01797 |
| Opus 5.5 | $0.00032 | $0.00719 |
| Sonnet 5.5 | $0.00016 | $0.00359 |
| Haiku 4.5 | $0.00008 | $0.00180 |
Grade A, and why
mdt-pipeline-e2e 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 2mo 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ticket Pipeline E2E
Run one ticket from intent to reviewed implementation. Own the control loop; load project docs, project-local skills, references, and tools only when needed.
Start Here
- Read root instructions and ticket docs.
- Run this skill's
scripts/discover_project.sh <repo-root> [ticket]when shell access is available. - Resolve the ticket source, artifact directory, current status, and existing artifacts.
- Write or update
.pipeline-state.jsonin the ticket artifact directory. - Run baseline verification from project docs or discovered package scripts.
- Start the milestone matrix below.
Core Rules
- Prefer project docs over this generic skill for paths, commands, statuses, durable docs, and verification.
- Read
docs/SKILLS.mdwhen present before selecting helper skills. - Do not hardcode MDT commands unless the project documents MDT or the user says "use MDT flow".
- Never close a ticket without explicit user approval.
- Keep the worktree scoped; never stash, reset, stage, or rewrite unrelated user changes.
- Record enough state on disk to resume after context loss.
Discovery Record
Record this before milestone 1:
Project docs: <files read>
Ticket source: <key/url/path/description>
Artifact directory: <path>
Ticket status model: <states and transition command, or none>
Workflow skills/tools: <project-local first, global fallback>
Language/runtime: <detected stack and selected references>
Verification commands: <baseline build/test/lint/docs commands>
Dirty worktree boundary: <unrelated files to avoid, or none>
State file shape:
{
"pipeline": "mdt-pipeline-e2e",
"version": 4,
"ticket": "<ticket key or source>",
"currentMilestone": "pre-flight",
"completedMilestones": [],
"discovery": {},
"artifacts": {},
"baseline": {},
"approvals": {},
"commits": [],
"updatedAt": "<ISO8601>"
}
References
Load only what applies:
| Reference | Load when |
|---|---|
references/mdt-workflow.md |
User says "use MDT flow" or MDT stage skills are available |
references/ux-gate.md |
UI, interaction, content, visual, or durable design-doc changes |
references/ralph-loop.md |
Ralph tools or equivalent milestone protocol are available |
references/language-typescript.md |
TypeScript, JavaScript, Node, Bun, npm, pnpm, yarn, React |
references/language-python.md |
Python, Django, Flask, FastAPI, pytest, uv, Poetry |
references/language-rust.md |
Rust, Cargo, crates, clippy |
references/language-go.md |
Go modules, go test, go vet |
What ships with it
9 files 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.
- 2mo ago First seen · 184 lines · 80 tokens per session scan A 4c6d6fee657b
mdt-pipeline-e2e is a skill published in the GitHub repository andkirby/markdown-ticket (7 stars, last pushed 5d ago), licensed MIT. It adds 80 tokens to every session and 1,797 once invoked, about $0.0003 per session on Opus 5.5. 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.
mdt-pipeline-e2e compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mdt-pipeline-e2eandkirby/markdown-ticket | Skill | 7 | 5d ago | MIT | A | 80 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |