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 rp1-run/rp1 --skill publish-artifactgit clone --depth 1 https://github.com/rp1-run/rp1Wrote 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/rp1-run/rp1/publish-artifact)<a href="https://agentmods.dev/skills/rp1-run/rp1/publish-artifact"><img src="https://agentmods.dev/badge/skills/rp1-run/rp1/publish-artifact/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/rp1-run/rp1/publish-artifact"><img src="https://agentmods.dev/badge/skills/rp1-run/rp1/publish-artifact.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 | $0.00052 | $0.01795 |
| Opus 5 | $0.00026 | $0.00898 |
| Sonnet 5 | $0.00010 | $0.00359 |
| Haiku 4.5 | $0.00005 | $0.00179 |
Grade A, and why
publish-artifact 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 4d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Publish Artifact
Publish an rp1 artifact (markdown under .rp1/work/; frontmatter optional) as a PR or issue comment without committing the artifact file to the repo. Re-running updates the same comment in place.
The artifact file is never modified by this skill — it is read-only on the local side, write-only on the GitHub side.
⚠️ Always dry-run first on a real PR or issue
The skill writes to a real GitHub PR/issue comment by default. Before publishing to a PR/issue you care about (especially one with active reviewers), run with
"dry_run": truefirst. A dry-run still resolves the target, validates, and runs the safety gates — it only skips the GitHub write — then returns the projecteddata.comment_bodyplus thedata.action(postorpatch) the real run would take. Once the projection looks right, re-run withoutdry_runto post.
When to invoke
- User explicitly runs
/rp1-dev:publish-artifact <path> [target]. - User has just produced an rp1 artifact and asks how to share it on a PR or issue without committing it.
- User asks to "summarize an rp1 investigation report into a PR or issue comment."
When NOT to invoke
- The file is not an rp1 work artifact at all (not under
.rp1/work/and unrelated to rp1). This skill publishes rp1 artifacts; frontmatter is optional, but the file should be an rp1 work product. - The user wants to keep the artifact in the repo. This skill is for the don't commit it case.
Gather the inputs
| Field | Required | How to determine |
|---|---|---|
artifact_path |
yes | The path to the artifact markdown the user wants to publish. A path outside .rp1/work/ is allowed (a warning is returned). |
target |
no | A PR/issue number or full GitHub PR/issue URL the user named. Omit it to default to the current branch's open PR. |
dry_run |
no | true when the user wants a preview, or on a first publish to a real target. Defaults to false (real post). |
force |
no | true only when the user explicitly wants to override a safety gate (closed/merged target, or a comment owned by another author). Defaults to false. See references/edge-cases.md. |
What ships with it
3 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.
- 4d ago First seen · 130 lines · 52 tokens per session scan A b17ca2ddfcfe
publish-artifact is a skill published in the GitHub repository rp1-run/rp1 (38 stars, last pushed 5d ago), licensed Apache-2.0. It adds 52 tokens to every session and 1,795 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 2026-09-07.
Other skills, from other repositories
git-workflow
A guide for handling Git repository work safely, including status checks, branches, commits, pushes, pull requests, and rebasing. Git is a version-control system that records code changes and coordinates work between developers.
changelog-gen
A changelog generator that turns Git history into a version-by-version record of project changes. A changelog is a readable summary of new features, fixes, breaking changes, documentation, and other updates.
at-daily-log
Summarize each day's Git activity into a concise daily work log, for a single date or a range. Uses the current repository, optional configured work projects, or paths named in conversation; configuration is never required.
at-commit
Generate a Conventional Commits message from staged changes and wait for confirmation before committing. Use when the user asks to commit or generate a commit message.
repo-hygiene
Use when auditing repo hygiene in any codebase — file layout, git history, config sprawl, ignore contracts, open-source readiness. Assess by default, fix on request; treats the repository as a product whose users are contributors.
openspec-bulk-apply-change
Use when multiple active OpenSpec changes should be applied concurrently in isolated worktrees with delegated verification and no merge.