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 product-on-purpose/agent-skills-toolkit --skill askit-capability-whats-newgit clone --depth 1 https://github.com/product-on-purpose/agent-skills-toolkitWrote 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/product-on-purpose/agent-skills-toolkit/askit-capability-whats-new)<a href="https://agentmods.dev/skills/product-on-purpose/agent-skills-toolkit/askit-capability-whats-new"><img src="https://agentmods.dev/badge/skills/product-on-purpose/agent-skills-toolkit/askit-capability-whats-new/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/product-on-purpose/agent-skills-toolkit/askit-capability-whats-new"><img src="https://agentmods.dev/badge/skills/product-on-purpose/agent-skills-toolkit/askit-capability-whats-new.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 | $0.00088 | $0.01854 |
| Opus 5 | $0.00044 | $0.00927 |
| Sonnet 5 | $0.00018 | $0.00371 |
| Haiku 4.5 | $0.00009 | $0.00185 |
Grade A, and why
askit-capability-whats-new 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 11d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
askit-capability-whats-new
Purpose
This repository asserts facts about software it does not control: what a runtime loads, what a manifest may declare, which component types a plugin can ship. Those facts reach the gate as normative text and as shipped findings, and every one of them was a page somebody read once.
Two machines already re-verify what we have written down. askit-standards-watch re-checks the agentskills.io specification against a pinned blob, and npm run vendor-watch re-checks pinned vendor sentences against the live page. Both answer the same question: did a fact we already depend on stop being true?
Neither answers the other question, and nothing did before this skill: what did the vendor ship that we have not looked at yet? A regression watch is blind to a new capability by construction, because a capability nobody has written down has no pin to fail.
This skill discovers and records. It owns docs/internal/capability-surveys/.
When to use
When someone asks what is new in Claude Code, Cowork, Codex or the upstream spec; before a release that will claim currency with the vendors; on a periodic sweep; or when a decision is about to rest on "the vendor probably supports that."
The one hard rule
This skill DISCOVERS and DOCUMENTS. It decides nothing.
It does not edit the capability matrix, a check module, STANDARD.md, vendor-claims.json, any pin other than its own proposed one, or a component's frontmatter. Deciding what a vendor change means for us is askit-capability-gap-analysis, and ratifying that is an ADR.
The separation is not bureaucratic. A survey that also proposed changes would be graded on how much it found, and a survey graded on volume stops reporting "nothing material", which is the most common and most useful result it produces.
Procedure
1. Read the pin, and never survey from a date
foundation/claims/surveyed-pin.json records, per surface, the version last surveyed. Start there.
What ships with it
6 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.
- 11d ago First seen · 100 lines · 88 tokens per session scan A 58544efb3c21
askit-capability-whats-new is a skill published in the GitHub repository product-on-purpose/agent-skills-toolkit (2 stars, last pushed today), licensed Apache-2.0. It adds 88 tokens to every session and 1,854 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
modelchk
Size a task's run before spending it: the cheapest sufficient capability tier (fast, standard, frontier) and the reasoning effort within it, on a neutral scale that binds to whatever levels the model exposes. Use when work seems over- or under-powered, costly, ambiguous, or high-risk, or asks which model class and how…
autobahn
Carve guardrail-adjacent items out of scope with safe alternatives before risk-adjacent work starts, then run the safe remainder at full strength in a fresh subagent that only ever sees the carved prompt, never the risky input. Use when a task includes stealth, scraping, privacy, IP, policy, licensing, security, or…
re0-release
Walk a pending change through this repo's shipping and releasing checklist end to end, then tag and publish once confirmed. User-invoked: run it when you've decided to ship.
ssotize
Audit and consolidate a fact that's scattered across places into one canonical source, after approval, and replace the rest with references. Use when asked to find duplication, check consistency, locate the source of truth, deduplicate, consolidate, unify, or establish SSOT across artifacts or platforms. Starts…
dedash
Remove em-dashes and the dashes standing in for them from a user-owned scope, reading each occurrence in context and choosing the punctuation or wording that fits.
feynman
Press a decision you just made until you can explain it to a skeptic in your own words, or surface the gap where you can't. The Feynman test aimed at a choice: understanding is cheapest to fake the moment after you decide, so a fresh critic presses for what you can't actually explain. Use right after picking an…