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 randommonicle/claude-skills --skill live-state-firstgit clone --depth 1 https://github.com/randommonicle/claude-skillsWrote 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/randommonicle/claude-skills/live-state-first)<a href="https://agentmods.dev/skills/randommonicle/claude-skills/live-state-first"><img src="https://agentmods.dev/badge/skills/randommonicle/claude-skills/live-state-first/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/randommonicle/claude-skills/live-state-first"><img src="https://agentmods.dev/badge/skills/randommonicle/claude-skills/live-state-first.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 | $0.00087 | $0.00713 |
| Opus 5 | $0.00044 | $0.00357 |
| Sonnet 5 | $0.00017 | $0.00143 |
| Haiku 4.5 | $0.00009 | $0.00071 |
Grade A, and why
live-state-first 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Live state first
The single most-repeated lesson on this machine: twelve-plus recurrences of building against a world that no longer exists — invented columns from a stale handover, a "still open" item carried across four handovers a month after it was done, an audit finding two migrations stale, a reviewer's citation superseded by a later migration. Layer: norm + playbook — the one-line norm in the global CLAUDE.md is the everyday trigger; this file is the depth.
The rule
Every document claim — including the repo's own comments, skills, and FORWARD notes — is a claim, not a fact. Before it becomes an input to code, SQL, config, or a fixture, verify it with one cheap probe of the live source. The latest migration, policy, or config is the truth; when two documents disagree, the catalog settles it.
How to apply
- One cheap probe before building: a catalog query for schema claims
(
information_schema,pg_policy,pg_get_functiondef), the deployed surface for behaviour claims, the actual config for settings claims. - The file is not the live object, in either direction. The live database routinely runs ahead of main (raw-applied unmerged migrations) and behind the repo (comments and fixes never applied). A migration file's text is evidence of intent, not of state.
- Query the live distribution, not just the schema, before building on a data assumption — 254 residue rows once would have shipped a correct feature looking broken.
- Structured data needs a parser, not a grep with context lines. Grep-with-context misled on JSON twice; scope schema greps to the block they describe.
- Staleness ranks: "still open" items in handovers, path hints in a repo's own docs, and audit trackers are the most likely claims to be stale — they record status at a moment, not state.
What this skill does not do
It does not probe repo state — fetch, PR lists, and identifier ceilings are parallel-work-recon's territory. It does not define migration verification (that is db-migration-verification's post-apply half; this skill is the pre-compose half).
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 · 50 lines · 87 tokens per session scan A 8e09c3fedde0
live-state-first is a skill published in the GitHub repository randommonicle/claude-skills (23 stars, last pushed 4d ago), licensed Apache-2.0. It adds 87 tokens to every session and 713 once invoked, about $0.0004 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.