Claude-Mind: Skill for Claude Code

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

verify-learning is a skill for Claude Code from zkysar1/Claude-Mind. It costs 101 tokens per session (2,423 once invoked), scanned A, original, MIT.

A post-test skill that checks whether an AI agent's learning records and supporting safeguards are present and up to date. It examines items such as stored knowledge, resolved hypotheses, reflections, and skill protocols.

In plain words
What is it for?
Use it after major learning cycles or when running the `/verify-learning` command to produce a checklist-based verification report.
Why use it?
It reveals missing or outdated learning artifacts after major changes or tests, so incomplete learning is not mistaken for finished work.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

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/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

README.md
[![agentmods](https://agentmods.dev/badge/skills/zkysar1/claude-mind/verify-learning.svg)](https://agentmods.dev/skills/zkysar1/claude-mind/verify-learning)
Your own site
<a href="https://agentmods.dev/skills/zkysar1/claude-mind/verify-learning"><img src="https://agentmods.dev/badge/skills/zkysar1/claude-mind/verify-learning.svg" alt="Measured on agentmods" height="20"></a>
Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,423 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 $0.00101 $0.02423
Opus 5 $0.00051 $0.01211
Sonnet 5 $0.00020 $0.00485
Haiku 4.5 $0.00010 $0.00242

Measured 7d ago against content hash 3a81ebf32241, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

verify-learning 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 7d 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/SKILL.md · 186 lines

How it starts

The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/verify-learning — Post-Test Verification

User-invocable AND agent-callable (hybrid skill).

Step 0: Load ConventionsBash: load-conventions.sh with each name from the conventions: front matter. Read only the paths returned (files not yet in context). If output is empty, all conventions already loaded — proceed to next step.

Step 1: Load Checklists

  1. Read core/config/verification-checklist.md (framework checklist).
  2. Read core/config/verification-checklist-domain-specific.md (foundational domain checklist template — see file header for the three-tier loading explanation).
  3. IF world/verification-checklist.md exists: Read it (agent-discovered domain checks). ELSE: Note "No agent-discovered domain checks — skipping."

Step 1.1: Load-Time Sanity (rot detection)

Counts active content lines per loaded file — BOTH Check:-prefixed lines AND numbered-discovery lines (leading \d+\. ). If any deployment-overlay file contributes ZERO of BOTH AND the deployment has ≥10 completed goals, emits a SOFT WARNING (does not fail verification). Catches the rot pattern where a deployment-specific checklist has silently become a stub. Created 2026-05-17 (Phase 1.2 packaging cleanup) after the domain template had silently been a 23-line stub since 2026-04-06 with no warning surfaced.

The OR-match on both prefix shapes was added 2026-05-19 (g-115-955) after a populated-but-prose overlay (world/verification-checklist.md with 81 numbered-discovery lines from alpha-era encode-session) false-triggered the "0 Check: lines" rot warning. Numbered ordered lists ARE substantive content when they enumerate discovered checks — the previous ^\s*Check:-only regex treated them as zero. Real rot looks like a 23-line stub; populated prose contributes either format and should PASS.

Check: domain-overlay verification checklists are not rotted to placeholder content. Bash: py -3 -c "import sys,re,pathlib,json; sys.path.insert(0,'core/scripts'); from _paths import WORLD_DIR; files=[('core/config/verification-checklist-domain-specific.md',pathlib.Path('core/config/verification-checklist-domain-specific.md')),('world/verification-checklist.md',WORLD_DIR/'verification-checklist.md')]; total=0; asp=WORLD_DIR/'aspirations.jsonl'; total = sum(sum(1 for g in __import__('json').loads(L).get('goals',[]) if g.get('status')=='completed') for L in asp.read_text(encoding='utf-8').splitlines() if L.strip()) if asp.exists() else 0; warns=[f'{label} loaded but 0 content lines (Check: or numbered-discovery) (deployment has {total} completed goals - likely rotted)' for label,p in files if p.exists() and sum(1 for L in p.read_text(encoding='utf-8').splitlines() if re.match(r'^\s*Check:|^\s*\d+\.\s',L))==0 and total>=10]; print('WARN: '+'; '.join(warns)) if warns else print(f'PASS: all loaded overlay checklists contribute content lines (deployment has {total} completed goals)')"

Read the full file on GitHub · 186 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. 7d ago First seen · 186 lines · 101 tokens per session scan A 3a81ebf32241

Subscribe to this mod's changes

verify-learning is a skill published in the GitHub repository zkysar1/Claude-Mind (5 stars, last pushed yesterday), licensed MIT. It adds 101 tokens to every session and 2,423 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

interview-prep

Technical interview preparation expert for algorithms, system design, and behavioral questions.

ginkida/rustyhand · 18 tokens

agent-challenges

Agent skill for challenges - invoke with $agent-challenges.

ruvnet/ruflo · 15 tokens

hive.browser-automation

Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…

aden-hive/hive · 142 tokens

hive.linkedin-automation

Read before automating LinkedIn with browser tools. LinkedIn combines shadow DOM (#interop-outlet), strict Trusted Types CSP that silently drops innerHTML, Lexical composer, native beforeunload dialogs that hang the bridge, and aggressive spam filters — each has bitten us at least once. Verified flows for profile…

aden-hive/hive · 99 tokens

hive.worker-delegation

Concrete patterns for breaking colony work into parallel worker jobs via runplaybook — when fan-out helps, how to model the goal as a tracker table, write the worker skill, author the playbook, pilot, and let convergence retry/resume the gap.

aden-hive/hive · 58 tokens

hive.slack-notifications-setup

Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…

aden-hive/hive · 136 tokens