What is agent-readiness?

A framework for checking how safely and effectively a coding agent can work in a software repository, using a transparent 82-criterion assessment.

Use it to audit or compare repositories, create readiness reports, set preferences, and improve one failing criterion at a time when authorized.

It reveals missing instructions, safeguards, or repository practices that could make agent-assisted development unreliable.

agent-readiness — Skill for Codex by zacharygcook/agent-skills

Install

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.

Any agent

npx skills add zacharygcook/agent-skills --skill agent-readiness

Clone the repo

git clone --depth 1 https://github.com/zacharygcook/agent-skills

Made for: Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/zacharygcook/agent-skills/agent-readiness/github.svg)](https://agentmods.dev/skills/zacharygcook/agent-skills/agent-readiness)

Your own site

<a href="https://agentmods.dev/skills/zacharygcook/agent-skills/agent-readiness"><img src="https://agentmods.dev/badge/skills/zacharygcook/agent-skills/agent-readiness/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/zacharygcook/agent-skills/agent-readiness"><img src="https://agentmods.dev/badge/skills/zacharygcook/agent-skills/agent-readiness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,360 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00081	$0.01360
Opus 5.5	$0.00032	$0.00544
Sonnet 5.5	$0.00016	$0.00272
Haiku 4.5	$0.00008	$0.00136

Measured 1mo ago against content hash bc034addb86e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-readiness 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 1mo ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/agent_eval.py, scripts/readiness.py, scripts/test_agent_eval.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/agent-readiness/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Readiness

Produce a personally owned, vendor-neutral readiness assessment from a transparent 82-criterion rubric. Prefer real engineering capability over score theater and make every judgment auditable.

Choose the operation

Audit-report: inspect and score without changing the repository, then generate HTML, PDF when local Chromium is available, Markdown, and JSON artifacts.
Initialize preferences: copy assets/DEFAULT_AGENT_READINESS_PREFERENCES.md to AGENT_READINESS_PREFERENCES.md in the repository root only when the user requests it or approves repository changes. Never overwrite an existing file.
Remediate-one: score, select one failing criterion, implement a durable repo-specific fix, validate it, rescore it, and commit only that fix when authorized.
Improve-to-target: repeat one criterion and one commit at a time until the requested owned percentage or level is reached, or a genuine blocker requires user authority.
Compare: compare two assessments or reports and make regressions visible even when the total score rises.

For audit-report or compare, read references/rubric.json and references/report-workflow.md completely. For remediate-one or improve-to-target, also read references/remediation-loop.md. Apply preferences in this order: explicit instructions in the current request, root AGENT_READINESS_PREFERENCES.md, then assets/DEFAULT_AGENT_READINESS_PREFERENCES.md. State which file was used. Preferences guide how to implement a capability; they are not standing permission to create or connect third-party accounts, accept costs, install external apps, add secrets, or mutate production.

Audit workflow

Read repository instructions and preferences before evaluating anything.
Record the current commit and dirty-tree state. Audits are read-only.
Discover deployable/runnable applications from source, manifests, workspace configuration, and deployment files. Libraries are applications only when independently built, tested, or shipped.
Evaluate all 82 criteria. Repository criteria receive one judgment. Application criteria receive one judgment per application: pass, fail, or not_applicable.
Use not_applicable only for skippable criteria and explain why that application is outside the criterion's actual risk surface. Never infer failure merely from inapplicability.
Require concrete evidence for every pass. Prefer source/config paths and successful commands; external-state criteria may cite CLI/API output. Do not award credit for prose claiming an implementation exists when the implementation is absent.
Create an assessment matching references/assessment-format.md. Record command and external-state checks in provenance.evidence_checks; store concise summaries, timestamps, and exit status rather than secrets or raw output.
Add repository-aware recommendations following references/report-workflow.md, then validate and render it with:

Read the full file on GitHub · 99 lines

Files

What ships with it

17 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.

Changes

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.

1mo ago First seen · 99 lines · 81 tokens per session scan A bc034addb86e

Subscribe to this mod's changes

agent-readiness is a skill published in the GitHub repository zacharygcook/agent-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 81 tokens to every session and 1,360 once invoked, about $0.0003 per session on Opus 5.5. 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.

Building agents Claude Code Testing agent-skills ai-agents codex coding-agents

nemo-automodel-recipe-development

Create and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution flow.

NVIDIA/skills · 31 tokens

mcore-testing

Test system for Megatron-LM. Covers test layout, recipe YAML structure, adding and running unit and functional tests, golden values, marker filters, and CI parity.

NVIDIA/skills · 38 tokens

i4h-catheter-navigation-e2e

End-to-end smoke for catheter navigation covering setup, digital twin, DRR, and unit tests. Use when asked to run the full catheter workflow smoke or demo the v0.7 pipeline.

NVIDIA/skills · 49 tokens

i4h-catheter-navigation-render-drr

Render a single DRR fluoroscopy frame from a CT cache or synthetic phantom. Use when asked to render DRR, generate a fluoro image, or smoke-test the Slang renderer.

NVIDIA/skills · 48 tokens

jetson-validate-image

Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.

NVIDIA/skills · 50 tokens

playwright-skill

Complete browser automation with Playwright. Auto-detects dev servers, writes reusable test scripts, and supports screenshots, responsive checks, UX validation, login flows, link checks, and arbitrary browser automation. Use when the user wants to test a website, automate browser interactions, validate web…

lackeyjb/playwright-skill · 69 tokens