loop-readiness-review

loop-readiness-review is a skill for Codex from markoblogo/abvx-agent-skills. It costs 58 tokens per session (940 once invoked), scanned A, original, MIT.

A review checklist for deciding whether recurring or semi-automatic coding-agent work is safe to run. It covers readiness levels from report-only work to governed loops with state, isolation, verification, budgets, and human approval.

In plain words
What is it for?
Use it to assess cron jobs, CI automation, scheduled agent tasks, issue triage, dependency updates, pull-request monitoring, and other repeated workflows.
Why use it?
It helps reveal missing safeguards before an agent repeatedly changes code, handles issues, watches pull requests, or runs scheduled maintenance.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Claude Code; mentions Codex; mentions OpenCode.

Good fit Use it to assess cron jobs, CI automation, scheduled agent tasks, issue triage, dependency updates, pull-request monitoring, and other repeated workflows.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/markoblogo/abvx-agent-skills/loop-readiness-review
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 markoblogo/abvx-agent-skills --skill loop-readiness-review
Clone the repo
git clone --depth 1 https://github.com/markoblogo/abvx-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.

agentmods badge for loop-readiness-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/loop-readiness-review/github.svg)](https://agentmods.dev/skills/markoblogo/abvx-agent-skills/loop-readiness-review)
Your own site
<a href="https://agentmods.dev/skills/markoblogo/abvx-agent-skills/loop-readiness-review"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/loop-readiness-review/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.

agentmods 80×15 button for loop-readiness-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/markoblogo/abvx-agent-skills/loop-readiness-review"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/loop-readiness-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 940 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00058 $0.00940
Opus 5 $0.00029 $0.00470
Sonnet 5 $0.00012 $0.00188
Haiku 4.5 $0.00006 $0.00094

Measured 10d ago against content hash f66be5ff24dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

loop-readiness-review 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 10d 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.

skills/loop-readiness-review/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Loop Readiness Review

Use this skill before turning repeated agent work into a scheduled or recurring loop.

Use When

  • a workflow may run on a cadence: cron, automation, /loop, GitHub Actions, or external scheduler;
  • a runner will open worktrees, inspect CI, triage issues, update changelogs, watch PRs, or sweep dependencies;
  • a SET bundle is being handed to a loop-capable orchestrator;
  • a report-only loop is being promoted toward auto-fix or PR creation;
  • you need to decide whether the loop is L0, L1, L2, or L3 ready.

Readiness Levels

  • L0: not loop-ready; missing state, verifier, or human gate.
  • L1: report-only; can read, summarize, and propose actions.
  • L2: proposal-first; can create retained output, worktree changes, or draft PRs behind review gates.
  • L3: governed loop; has state, isolation, verifier, budget, run log, rollback/escalation, and human-controlled settlement.

Readiness Checks

Review:

  • cadence: trigger, frequency, quiet hours, stop rule;
  • state: STATE.md, run ledger, or other durable memory outside the model;
  • scope: allowed repos, paths, issues, branches, and denied targets;
  • isolation: worktree, branch, sandbox, or retained-output directory;
  • skills: triage, implementer, verifier, review lenses, and escalation roles;
  • connectors: MCP, GitHub, CI, email, calendar, or other external tools with least privilege;
  • verifier: deterministic checks, bounded eval, CI, human review, or maker/checker split;
  • budget: token, time, run count, retry, and spend caps;
  • run log: what happened, what changed, what failed, and why it stopped;
  • human gate: approval boundary for writes, merges, releases, destructive actions, or external side effects;
  • rollback: how to discard, revert, close, or pause the loop.

Workflow

  1. Identify the loop pattern and intended cadence.
  2. Classify the current readiness level.
  3. Check the readiness dimensions above.
  4. List blockers that prevent promotion to the next level.
  5. Recommend the smallest next step:
    • keep report-only;
    • add state file or run log;
    • add verifier;
    • add worktree isolation;
    • add budget caps;
    • add human gate;
    • stop or de-schedule the loop.

Read the full file on GitHub · 94 lines

Files

What ships with it

2 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.

  1. 10d ago First seen · 94 lines · 58 tokens per session scan A f66be5ff24dd

Subscribe to this mod's changes

loop-readiness-review is a skill published in the GitHub repository markoblogo/abvx-agent-skills (16 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 940 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 2026-08-30.