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 techtalk/ai-readiness-assessment --skill ai-readiness-rollupgit clone --depth 1 https://github.com/techtalk/ai-readiness-assessmentWrote 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/techtalk/ai-readiness-assessment/ai-readiness-rollup)<a href="https://agentmods.dev/skills/techtalk/ai-readiness-assessment/ai-readiness-rollup"><img src="https://agentmods.dev/badge/skills/techtalk/ai-readiness-assessment/ai-readiness-rollup/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/techtalk/ai-readiness-assessment/ai-readiness-rollup"><img src="https://agentmods.dev/badge/skills/techtalk/ai-readiness-assessment/ai-readiness-rollup.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 | $0.00113 | $0.05144 |
| Opus 5 | $0.00056 | $0.02572 |
| Sonnet 5 | $0.00023 | $0.01029 |
| Haiku 4.5 | $0.00011 | $0.00514 |
Grade A, and why
ai-readiness-rollup 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 — 502 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Readiness Portfolio Roll-up
Self-contained instrument for summarising AI readiness across several
subjects, using assessments that already exist. Does not depend on the
ai-literacy-superpowers plugin or any other plugin being installed.
The canonical entry point is the slash command /ai-readiness-rollup.
When invoked via natural language ("roll up our assessments", "how do
our repos compare"), follow the process below directly — the content is
identical.
When to use this skill
Use it when assessments already exist in more than one repository and
the question is how they compare. Use /ai-readiness-assess instead
when any individual subject has no assessment yet — a roll-up reads
reports, it does not produce them.
What a roll-up is
A roll-up reads the machine-readable assessment-summary block from
reports that already exist and assembles them into one portfolio view.
It runs no scan, asks no behavioural questions, and writes no per-subject
report.
That restraint is the design. Twelve repositories at ten minutes each, with the behavioural questions asked twelve times, is not a session anyone sits through, and a single pass over twelve repositories exhausts context long before it finishes. Reading artefacts instead of re-assessing also separates who runs the assessment from who reads the summary, which is what a consultancy engagement actually needs: each team keeps and owns its own report, and the portfolio view is assembled from what they produced.
The unit
The assessment unit is subject × governing habitat, with the cognitive read scoped to the team:
- Subject — the code artefacts under examination: a repository, a submodule, or a directory inside a monorepo.
- Habitat — the harness and control surfaces governing that subject.
- Team — the people whose behaviour produces the cognitive read. Never a repository.
What the roll-up is for
One cognitive read measured against N different habitats produces N different gaps, and the spread of those gaps is the headline finding. A team can sit Coherent in the greenfield service and deep in Ambition-outpaces-enablement in the legacy one. The enablement work those two facts imply is completely different, and a single-repository assessment cannot surface the difference because it only ever has one reading to compare.
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 · 502 lines · 113 tokens per session scan A 09ff007e5cd5
ai-readiness-rollup is a skill published in the GitHub repository techtalk/ai-readiness-assessment (9 stars, last pushed 24d ago), licensed Apache-2.0. It adds 113 tokens to every session and 5,144 once invoked, about $0.0006 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
learning-analytics-interpretation-guide
Interpret learning analytics data and translate dashboard findings into actionable teaching decisions. Use when reviewing LMS data, quiz patterns, or engagement metrics.
criterion-referenced-rubric-generator
Generate a criterion-referenced rubric with descriptive performance levels for a task or objective. Use for marking guides and general curriculum contexts. For Manning programmes where Competent = success, use coherent-rubric-logic-builder instead.
feedback-quality-analyser
Analyse existing written feedback for quality, specificity, actionability, and impact on student learning. Use when reviewing teacher or peer feedback to improve feedback practices.
retrieval-practice-generator
Generate retrieval practice questions at varied difficulty levels for a topic or concept. Use when creating quiz starters, revision activities, or low-stakes testing materials.
faf-context
Use FAF project context tools on this server — init, score, sync, discover; claim equals wire.
advocatus-diaboli
Use when acting as the adversarial spec reviewer — raises steel-manned objections across six categories before plan approval, requires evidence per objection, and discloses what was not challenged.