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.
git 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/commands/techtalk/ai-readiness-assessment/ai-readiness-assess)<a href="https://agentmods.dev/commands/techtalk/ai-readiness-assessment/ai-readiness-assess"><img src="https://agentmods.dev/badge/commands/techtalk/ai-readiness-assessment/ai-readiness-assess/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/commands/techtalk/ai-readiness-assessment/ai-readiness-assess"><img src="https://agentmods.dev/badge/commands/techtalk/ai-readiness-assessment/ai-readiness-assess.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 | $0.00068 | $0.13479 |
| Opus 5 | $0.00034 | $0.06739 |
| Sonnet 5 | $0.00014 | $0.02696 |
| Haiku 4.5 | $0.00007 | $0.01348 |
Grade A, and why
ai-readiness-assess 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 — 1,052 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ai-readiness-assess
Run an AI literacy assessment for this project against the framework set out in The Sovereign Engineer (Russ Miles, Habitat-Thinking).
This command is fully self-contained — it does not depend on any plugin skills, agents, sub-commands, or external services. Everything it needs to score is below.
The model (embedded)
This instrument evaluates a team's habitat against the Agentic Experience 5-Level Habitat Maturity Model — fourteen dimensions, each placed L1–L5. The model is the primary spine of the assessment: it describes what the team's habitat actually delivers.
Folded in as a second, cognitive read is the six-level ladder and three disciplines from The Sovereign Engineer (Russ Miles, Habitat-Thinking) — what the team can think and do. The Habitat/Workflow Gap measures coherence between the two reads.
Everything needed to score is below. This command is fully self-contained — it does not read from another repo, plugin, or service at runtime.
The fourteen dimensions (the spine)
Verbs in bold, key nouns plain. Each row is a dimension; each column is a maturity level. This is the model in full — every dimension is placed for every assessment.
| Dimension | L1 | L2 | L3 | L4 | L5 |
|---|---|---|---|---|---|
| Agent behaviour | Dictating | Commanding (prompting) | Regulating | Orchestrating | Supervising |
| Agent input | short ad-hoc prompts | larger prompts, commands | plans co-authored with an agent | iteratively refined specs | refined specs + customer/observable metrics |
| Workflow | safe runtime, generic | prompts/commands saved | harness engineered | workflow defined | workflow automated (agentic runtime) |
| Operating model | Chat with agent | Prompt-engineering | humans drive / verify | humans in the loop | humans certify |
| Teams provide | — | basic team-specific constitution | comprehensive product-specific constitution | full product-specific constitution | custom product-specific runtime |
| Output role (I am…) | Running | Inspecting | Standardising | Specifying | Certifying |
| Output artefact | executable / artifact | code | process & consistency rules | clear criteria | evidence |
| Humans review | output only | code | implementation in detail | specs | comprehensive evidence |
| Work patterns | partial task completion | small task completion | e2e development | semi-autonomous work | mostly-autonomous |
| Agent composition | single | single + saved patterns | primary + read-only critics | bounded ensemble (harness-composed) | self-orchestrating constellations |
| Agents… | Assist individuals | Complete basic tasks | Develop small changes (stories) | Implement larger changes (epics) | Implement larger changes autonomously |
| Testing | Manual inspection | Asserting (unit tests) | Verifying (functional / business) | Validating (comprehensive automation) | Assuring (multi-perspective + post-deploy) |
| Observability | Eyeballs | Captured | Instrumented | Aggregated | Closed loop |
| Governance | trust-based, ambient | conventional | Constitutional | Policy-as-code | Continuous certification |
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 · 1,052 lines · 68 tokens per session scan A 6bf4ffdbbbfd
ai-readiness-assess is a command published in the GitHub repository techtalk/ai-readiness-assessment (9 stars, last pushed 24d ago), licensed Apache-2.0. It adds 68 tokens to every session and 13,479 once invoked, about $0.0003 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 commands, from other repositories
cost-estimate
Estimate a target's tokens, agent-compute time, and (when grounded) cost before it runs — the prospective sibling of /cost-capture. Dispatches the read-only cost-estimator agent, validates the returned record, and writes it after you dispose.
harness-sync
Detect drift across all push-direction control surfaces, present the full picture, and apply the user's selected fixes via the existing primitives — single human-instigated entry point for keeping convention files in sync with HARNESS.md. ONBOARDING.md staleness is surfaced but not auto-fixed; users run…
pipeline-map
Render the task-scoped conceptual pipeline map for a work task you are considering. /pipeline-map " " drives the diagnostic-legibility agent in mode:pipeline (resolve bound → trace flow → three-way cross-check) and renders the bounded pipeline as a self-contained HTML flowchart (vendored, SHA-pinned Mermaid inlined…
harness-init
Set up a living harness for this project — select features, discover the stack, define conventions, generate HARNESS.md with enforcement. Re-run to add features incrementally.
superpowers-status
Show the complete health of the project's AI Literacy habitat — harness enforcement, agent team, compound learning, model routing, and CI status.
diagnose
Surface the mutually-corrected legibility models for a codebase scope on demand. /diagnose drives the full diagnostic-legibility pipeline (build, self-challenge, cross-check) and renders the corrected architectural and domain models as a readable markdown report.