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 jschulte/claude-plugins --skill deliver-megit clone --depth 1 https://github.com/jschulte/claude-pluginsWrote 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/jschulte/claude-plugins/deliver-me)<a href="https://agentmods.dev/skills/jschulte/claude-plugins/deliver-me"><img src="https://agentmods.dev/badge/skills/jschulte/claude-plugins/deliver-me/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/jschulte/claude-plugins/deliver-me"><img src="https://agentmods.dev/badge/skills/jschulte/claude-plugins/deliver-me.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 | $0.00076 | $0.01296 |
| Opus 5.5 | $0.00030 | $0.00518 |
| Sonnet 5.5 | $0.00015 | $0.00259 |
| Haiku 4.5 | $0.00008 | $0.00130 |
Grade A, and why
deliver-me 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 24d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deliver Me
One request in, one reviewed and verified pull request out. No check-ins on the way: decide, write the decision down, keep going.
Core principle: the change should read as if this codebase's own team wrote it on a careful day, and every claim in the final report is something you observed.
Done means all four
- The work is committed on its own branch, pushed, with a PR open. No remote: committed on a branch, and the report says so. Never uncommitted, never on the default branch.
- It fits the codebase (Phase 2).
- It is verified at the highest rung available (Phase 6).
- The report has the fixed shape below.
Stop early only for a missing credential, or an action that is destructive or cannot be undone (production deploy, live-data migration, force-push, deletion). Finish everything else first, then report the one thing you left.
Phases
0. Ground. Read the repo's own rules (CLAUDE.md, AGENTS.md, CONTRIBUTING, definition of done); they override this skill. Look for an open PR, branch or issue that already covers the request and continue it instead of competing. Create the branch now; use a separate worktree if the checkout is dirty or shared.
1. Understand. State the outcome in one sentence and the checks that would prove it. Reproduce the bug or show the gap before changing anything. Where the request is ambiguous, take the reading that is safest for users and their data, and record it as a decision.
2. Fit. Before designing, read the nearest existing thing of the same kind, end to end, with its tests. Then fill in this table. It is required. It goes in the PR body; with no PR, it goes in the commit body.
| Need | Reuse | Where |
|---|---|---|
| Entry point and registration | ||
| Auth and permissions | ||
| Input validation | ||
| Data access | ||
| Units and formatting | ||
| Response and error shape | ||
| Tests and test helpers | ||
| Docs, lists and scripts that enumerate this kind of thing |
A row may say "new" only after a search you can name. Extend a helper before forking it.
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.
- 24d ago First seen · 108 lines · 76 tokens per session scan A 93900e948d9c
deliver-me is a skill published in the GitHub repository jschulte/claude-plugins (0 stars, last pushed 25d ago), licensed MIT. It adds 76 tokens to every session and 1,296 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 2026-10-12.
Other skills, from other repositories
github-copilot-upgrader
Use this to update the Github Copilot CLI/SDK.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
meta-pre-commit-quality-gate
Run three quality gates (ruff + mypy + pytest) in parallel over the staged diff, then arbitrate a single BLOCK/APPROVE verdict. Use before committing changes locally when you want a comprehensive pre-commit gate beyond per-file linting — exactly the same gate set CI enforces.
verify-commit
Verify that commits for a GitHub issue include tests and that those tests fail without the implementation changes. Given an issue ID, finds commits, checks for test files, then reverts src/main changes and runs the tests to confirm they fail.
nw-quality-framework
Quality gates - 11 commit readiness gates, build/test protocol, validation checkpoints, and quality metrics.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.