Agentero is a local research workspace that connects papers, structured reading material, Markdown notes, and AI agents in one place. Researchers use it to read and annotate PDFs, extract formulas and figures, organize literature, and collaborate with agents on research tasks while keeping context locally. Its catalogue skills and instruction support agent-assisted research workflows in Agentero.
Borrowing it
Nothing to install: this file belongs to poco-ai/Agentero. 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/poco-ai/Agentero/main/.agents/skills/release/SKILL.mdgit clone --depth 1 https://github.com/poco-ai/AgenteroWrote 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/poco-ai/agentero/release)<a href="https://agentmods.dev/skills/poco-ai/agentero/release"><img src="https://agentmods.dev/badge/skills/poco-ai/agentero/release/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/poco-ai/agentero/release"><img src="https://agentmods.dev/badge/skills/poco-ai/agentero/release.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 | $0.00081 | $0.01647 |
| Opus 5.5 | $0.00032 | $0.00659 |
| Sonnet 5.5 | $0.00016 | $0.00329 |
| Haiku 4.5 | $0.00008 | $0.00165 |
Grade A, and why
release 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 1mo 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentero Release
Prepare evidence-backed bilingual Release notes and write them directly to the Draft GitHub Release. Use dry runs when the user explicitly requests read-only preview.
Establish the release range
- Read
git status, the current branch, local and remote tags, and the target Release state. Preserve unrelated working-tree changes. - Resolve both endpoints to immutable commits and verify that the base is an ancestor of the target.
- For a stable target, default to the latest earlier published stable Release reachable from the target. For a prerelease, prefer the preceding prerelease in the same version series, then fall back to the latest stable Release.
- Display the selected
<base>..<target>range. Stop for user direction when the target, release channel, ancestry, or previous Release is ambiguous. - Never move or overwrite an existing remote tag. Treat a tag already observed by GitHub Actions or attached to a Release as immutable.
Collect evidence
Run the bundled collector from the repository root:
node .agents/skills/release/scripts/collect-release-context.mjs <base> <target>
Use merged pull requests as the main narrative units. Always inspect uncovered first-parent commits as a second source; the presence of one PR does not make other mainline commits disappear.
For each candidate change:
- Prefer the PR title, body, linked issues, labels, and changed behavior.
- Use the first-parent commit subject, body, and changed files when no merged PR covers the commit.
- Inspect the relevant diff or documentation when the public effect is unclear.
- Collect issues closed during the release range that are not already covered by
a merged PR. Use
gh issue list --state closed --search "closed:>={base-date}"or inspectCloses/Fixesreferences in commit messages. - Exclude release bumps, formatting, tests, internal refactors, and routine documentation unless they change installation, compatibility, security, or visible behavior.
- Combine multiple commits that implement one user-visible outcome.
- Keep a PR, commit, or issue URL as evidence for every bullet.
- Include the first committer or PR author for each bullet so contributors are
credited in the notes. Resolve GitHub usernames — the git commit author
name (e.g.
QiyuanChen) is not necessarily the GitHub handle (e.g.qychen2001). For PRs, use the PRauthor.loginfield directly. For uncovered commits, rungh api repos/poco-ai/Agentero/commits/<sha>and extract theauthor.loginfield. Fall back to the commitauthor.nameonly when the GitHub API returns null (e.g. unauthenticated local commits). - Report uncertainty or conflicting evidence instead of inventing behavior.
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.
- 1mo ago First seen · 178 lines · 81 tokens per session scan A 3adcbb3febf5
release is a skill published in the GitHub repository poco-ai/Agentero (1,032 stars, last pushed today), licensed MIT. It adds 81 tokens to every session and 1,647 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 2026-08-30.
Other skills, from other repositories
GitHub PR Workflow
Move cleanly through branch, diff, review, validation, and PR update steps without losing scope or repository-native workflow.
open-code-review
Performs AI-powered code review on Git changes using the ocr CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply…
hunk-launch-video
Produces Hunk videos by driving the real TUI headlessly in a PTY, compositing captioned 1080p frames in Chromium, and encoding with ffmpeg. Use for feature demos, workflow explainers, announcements, launch videos, and full-release roundups.
github
GitHub operations via gh CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: complex web UI interactions requiring manual browser flows (use browser tooling when available)…
git
Git and code hosting platform management — GitHub, GitLab, Codeberg, Forgejo. Zero barrier — install x-cmd and manage repos from the terminal. Use for "git", "github", "gitlab", "repo", "pull request", "code hosting".
meta-codereview-current-diff
Read the current uncommitted diff, run three independent reviewers (safety + tests-coverage + style) in parallel, then arbitrate a single BLOCK / BLOCKWITHOVERRIDE / PASSWITHNOTES verdict. Use before commit when you want a multi-perspective second-opinion instead of a single-reviewer agent loop.