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 IgorWarzocha/howaboua-pi-stuff --skill repository-deliverygit clone --depth 1 https://github.com/IgorWarzocha/howaboua-pi-stuffWrote 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/igorwarzocha/howaboua-pi-stuff/repository-delivery)<a href="https://agentmods.dev/skills/igorwarzocha/howaboua-pi-stuff/repository-delivery"><img src="https://agentmods.dev/badge/skills/igorwarzocha/howaboua-pi-stuff/repository-delivery/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/igorwarzocha/howaboua-pi-stuff/repository-delivery"><img src="https://agentmods.dev/badge/skills/igorwarzocha/howaboua-pi-stuff/repository-delivery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00022 | $0.00616 |
| Opus 5 | $0.00011 | $0.00308 |
| Sonnet 5 | $0.00004 | $0.00123 |
| Haiku 4.5 | $0.00002 | $0.00062 |
Grade A, and why
repository-delivery 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 12d 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
Apply repository instructions as local constraints. Read the relevant request, issue, pull request, discussion, and reviews. Explicit user direction resolves genuine conflicts.
Before commit, branch, or history work, inspect the working tree, unrelated changes, current branch, upstream, remote default and target branches, and any existing pull request.
Authorization:
- Record coherent working states when useful and finish requested repository edits committed. Do not wait for a separate instruction to commit unless the user asked for uncommitted work or repository instructions require it.
- Opening a pull request authorizes its normal branch, commit, push, and creation steps.
- Updating a pull request or addressing its review authorizes committing and pushing in-scope fixes.
- Filing or updating an issue authorizes publishing that issue, not implementing it. Drafting a body alone does not authorize publishing it. Opening a pull request does not authorize requesting review or merging it.
Preserve unrelated work. Proceed around it when safe. Ask only when it blocks the requested result.
When multiple accounts or contributors are possible, verify GitHub and commit identity before the first commit or push. Never switch accounts silently, misattribute work, approve your own pull request, or bypass protection through another identity.
Read only the needed branch:
- Issue creation or update:
references/issues.md - Pull request creation, update, review, stacking, or landing:
references/pull-requests.md
Commits
- Stage deliberately and inspect the staged diff. Exclude unrelated edits, temporary diagnostics, local artifacts, and another task's work.
- Make each commit one coherent, inspectable state. Split when states can be understood, accepted, reordered, or reverted independently, when a stack needs layers, or when comparison and rollback are useful. Do not split by file count or elapsed time. Keep directly supporting tests, docs, migrations, and generated artifacts together.
- Write the subject from the staged effect with concrete domain nouns and an active verb. Follow repository grammar and prefixes. Avoid vague subjects such as
Fix bug,Update files,Changes, orWIP, plus branch names and ticket numbers alone. - Add a body only for reasons, prior behavior, constraints, trade-offs, compatibility, migrations, or deliberate limitations not clear from the subject and diff. Do not narrate files, commands, session history, or agent involvement. Follow established signing and trailer conventions. Preserve verified authorship. Never invent attribution.
- Do not keep a pull request as one repeatedly amended commit. Amend only a small immediate correction that completes the same commit when the earlier state has no diagnostic or review value. Use a new commit for a materially different state, alternative approach, later behavior fix, or review fix worth comparing. Preserve useful states until testing and review converge. Let merge policy squash them. Never rewrite published shared commits.
What ships with it
2 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.
- 12d ago First seen · 34 lines · 22 tokens per session scan A 98700425f5a1
repository-delivery is a skill published in the GitHub repository IgorWarzocha/howaboua-pi-stuff (368 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 616 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 2026-08-30.
Other skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.
git-commit
Generate well-formatted git commit messages following conventional commit standards.
repo-sync
Manage repo-sync on macOS for shared documents and team context. Use when asked what repo-sync does, to automatically sync a repo, add a repo to repo-sync, stop syncing or un-sync a repo, check sync health, configure repo-sync, uninstall it, or install and maintain its bundled agent skill. Ordinary one-time Git pulls…
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
contributing
How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.