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-gap-analysisgit 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-gap-analysis)<a href="https://agentmods.dev/skills/product-on-purpose/agent-skills-toolkit/askit-capability-gap-analysis"><img src="https://agentmods.dev/badge/skills/product-on-purpose/agent-skills-toolkit/askit-capability-gap-analysis/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-gap-analysis"><img src="https://agentmods.dev/badge/skills/product-on-purpose/agent-skills-toolkit/askit-capability-gap-analysis.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 | $0.00099 | $0.02063 |
| Opus 5 | $0.00049 | $0.01032 |
| Sonnet 5 | $0.00020 | $0.00413 |
| Haiku 4.5 | $0.00010 | $0.00206 |
Grade A, and why
askit-capability-gap-analysis 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 9d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
askit-capability-gap-analysis
Purpose
askit-capability-whats-new answers what shipped upstream. This skill answers the harder question: what does that mean for us?
Three separate things can be true of one finding, and conflating them is how a capability gets adopted for the wrong reason:
| Question | Owner |
|---|---|
| Does the capability matrix describe it? | this skill, directly |
| Should the Standard model it? | an ADR. This skill drafts; a human ratifies |
| Do our own components use or need it? | this skill, per component |
It owns foundation/synthesis/capability-matrix.md. askit-capability-advisor reads that file to advise an author; this skill is what keeps it true.
When to use
After a survey reports a capability finding; when deciding whether a new agent capability belongs in the Standard; when asking which components were last verified against an older agent version; or before a release that claims to be current with the vendors.
The one hard rule
This skill PROPOSES. A human ratifies.
It may update the capability matrix, because that is a description of the world and it owns it. It may not edit a check module, STANDARD.md, library.json, or vendor-claims.json.
One carve-out in component frontmatter, and only one: metadata.verified-against, on components this run actually assessed. references/component-staleness.md assigns that key to this skill by name and explains why it can belong to no other - a survey examines vendors rather than components, so a bulk stamp from a survey run asserts readings that never happened. Everything else in a component's frontmatter is still off limits. Stamping a version onto a component nobody re-read is the defect this key exists to prevent, so the carve-out is exactly as wide as "components you assessed" and no wider.
A capability finding is never itself a reason to add a check. The Standard grows only by ADR, with the warn-first burndown of STANDARD.md sec 7.7, and this repository has measured what happens when that order is skipped: a recommendation that looks obvious before measurement is overturned by measurement about as often as not.
What ships with it
5 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.
- 9d ago First seen · 105 lines · 99 tokens per session scan A 0f8224d68675
askit-capability-gap-analysis is a skill published in the GitHub repository product-on-purpose/agent-skills-toolkit (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 99 tokens to every session and 2,063 once invoked, about $0.0005 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…
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…
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.
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…
re0-git
Rewrite a finished commit's message into a clean, handoff-ready form in your own log style, so git log alone tells the story. User-invoked: run it after a commit.