Claude-Mind: Skill for Claude Code

.claude/skills/verify-learning-staleness/SKILL.md

verify-learning-staleness is a skill for Claude Code from zkysar1/Claude-Mind. It costs 195 tokens per session (1,614 once invoked), scanned A, original, MIT.

A checker for finding outdated verification instructions in verify-learning/SKILL.md. It checks whether referenced paths, headings, and search patterns still exist in the codebase.

In plain words
What is it for?
Use it to scan verification assertions and receive JSON or human-readable reports about stale references.
Why use it?
It helps prevent checks from appearing to pass when they refer to files or instructions that have been moved, renamed, or removed.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: reads .claude/ paths.

This is zkysar1/Claude-Mind's own configuration. It tells Claude Code how to work on Claude-Mind itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Claude-Mind configures →

Reuse

Borrowing it

Nothing to install: this file belongs to zkysar1/Claude-Mind. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/zkysar1/Claude-Mind/main/.claude/skills/verify-learning-staleness/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/zkysar1/Claude-Mind

Made for: Claude Code.

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 verify-learning-staleness

README.md
[![agentmods](https://agentmods.dev/badge/skills/zkysar1/claude-mind/verify-learning-staleness/github.svg)](https://agentmods.dev/skills/zkysar1/claude-mind/verify-learning-staleness)
Your own site
<a href="https://agentmods.dev/skills/zkysar1/claude-mind/verify-learning-staleness"><img src="https://agentmods.dev/badge/skills/zkysar1/claude-mind/verify-learning-staleness/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 verify-learning-staleness

Your own site · 80×15
<a href="https://agentmods.dev/skills/zkysar1/claude-mind/verify-learning-staleness"><img src="https://agentmods.dev/badge/skills/zkysar1/claude-mind/verify-learning-staleness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 195 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,614 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 $0.00195 $0.01614
Opus 5 $0.00097 $0.00807
Sonnet 5 $0.00039 $0.00323
Haiku 4.5 $0.00019 $0.00161

Measured 10d ago against content hash a762f5c31772, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

verify-learning-staleness 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.

.claude/skills/verify-learning-staleness/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/verify-learning-staleness — Verify-Learning Staleness Scanner

Detect stale Check: and Bash: assertions in verify-learning/SKILL.md whose underlying targets (paths, phase headers, grep patterns) have been moved, renamed, or extracted out of the codebase without the check being updated.

Why This Exists

verify-learning/SKILL.md accumulates ~2000 verification assertions over time. Each assertion references a concrete artifact: a script path, a SKILL.md phase number, a grep pattern in a named file. When refactors happen — extracting inline pseudocode into Python, renumbering phases, deleting retired scripts — the verification check goes stale silently. Future /verify-learning runs report PASS for stale checks because the assertion can't even be evaluated against current code, producing false confidence.

This skill is the structural complement: it scans every assertion and reports which ones reference artifacts the codebase no longer contains.

Companion Script

  • core/scripts/verify-learning-staleness.py — the canonical scanner. Modes:
    • Default (no flag) — JSON to stdout, exit 0 if clean / exit 1 if stale.
    • --text — human summary on stdout, JSON to stderr.
    • --skill-md <path> — override the target file (default: framework path).

Procedure

  1. Bash: py -3 core/scripts/verify-learning-staleness.py --text — run the scanner. Output lists each stale finding as [L<lane>] line N: <stale_ref> with detail explaining why the target couldn't be resolved.

  2. For each finding, decide the disposition:

    • Relocated — the underlying contract still exists, but moved to a different file/phase/script. Update the Check: text to reference the new location.
    • Retired — the contract was removed entirely. Delete the Check: line.
    • Future-tense — the check was added speculatively for upcoming work. Leave alone if work is genuinely imminent, otherwise convert to a comment or delete.
  3. After applying fixes, re-run the scanner — stale_count should ratchet down (or stay constant only with documented future-tense exemptions).

Read the full file on GitHub · 133 lines

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 · 133 lines · 195 tokens per session scan A a762f5c31772

Subscribe to this mod's changes

verify-learning-staleness is a skill published in the GitHub repository zkysar1/Claude-Mind (5 stars, last pushed 2d ago), licensed MIT. It adds 195 tokens to every session and 1,614 once invoked, about $0.0010 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.