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 OneWave-AI/open-agent-stack --skill scan-releasesgit clone --depth 1 https://github.com/OneWave-AI/open-agent-stackWrote 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/onewave-ai/open-agent-stack/scan-releases)<a href="https://agentmods.dev/skills/onewave-ai/open-agent-stack/scan-releases"><img src="https://agentmods.dev/badge/skills/onewave-ai/open-agent-stack/scan-releases.svg" alt="Measured on agentmods" 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 | $0.00071 | $0.00525 |
| Opus 5 | $0.00036 | $0.00262 |
| Sonnet 5 | $0.00014 | $0.00105 |
| Haiku 4.5 | $0.00007 | $0.00052 |
Grade A, and why
scan-releases 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 6d 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 — 27 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scan Releases
Find recent AI model and tool activity, then report only what matters to the user's stack. This skill needs live web access; use the built-in web tool. No API key is required.
Workflow
- Establish the stack. Ask the user which models, APIs, SDKs, and tools they depend on, or infer from the project (package manifests, config files, env var names). Record exact names and current versions.
- Establish the time window. Default to the last 14 days unless the user gives a date or range. Note the cutoff date explicitly.
- Build the source list. For each stack item, identify its official release notes, changelog, and deprecation or end-of-life page. See
references/sources.mdfor canonical URLs by vendor and how to find missing ones. - Fetch each source with the web tool. Read the actual pages; do not rely on memory or summaries. Capture version, date, and the concrete change for every entry inside the window.
- Classify each entry as Release, Change, or Deprecation. Drop entries older than the cutoff. Discard marketing items with no behavioral or version impact.
- Flag stack impact. Mark every entry that touches a declared stack item. For each flagged item, assign severity using
references/impact-rubric.md(breaking, behavioral, additive, informational). - Recommend an action per flagged item: migrate now, plan migration before a stated cutoff, adopt optionally, or no action. Include the deprecation deadline when one exists.
- Verify before reporting. Confirm each claim against its source URL, dates are within the window, and version strings are exact. Drop anything you cannot source.
- Report using the format in
references/report-format.md: a short stack-impact section first (sorted by severity), then a brief other-activity section. Cite the source URL for every item.
Rules
- Source every claim with a live URL. No unsourced or remembered releases.
- Lead with what affects the user. Keep non-impacting activity to one line each.
- State exact versions, dates, and deprecation deadlines. Avoid vague terms like "recently."
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.
- 6d ago First seen · 27 lines · 71 tokens per session scan A 2f4c3700b5a4
scan-releases is a skill published in the GitHub repository OneWave-AI/open-agent-stack (2 stars, last pushed 26d ago), licensed MIT. It adds 71 tokens to every session and 525 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
outlines
Outlines: structured JSON/regex/Pydantic LLM generation.
weights-and-biases
W&B: log ML experiments, sweeps, model registry, dashboards.
guidance
Constrain LLM output with grammars; guarantee valid JSON.
huggingface-tokenizers
Fast BPE/WordPiece tokenization and custom vocab training.
instructor
Structured LLM outputs validated with Pydantic.
obliteratus
OBLITERATUS: abliterate LLM refusals (diff-in-means).