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.
curl -O https://raw.githubusercontent.com/zkysar1/Claude-Mind/main/.claude/skills/verify-learning/SKILL.mdgit clone --depth 1 https://github.com/zkysar1/Claude-MindWrote 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/zkysar1/claude-mind/verify-learning)<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>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 | $0.00101 | $0.02423 |
| Opus 5 | $0.00051 | $0.01211 |
| Sonnet 5 | $0.00020 | $0.00485 |
| Haiku 4.5 | $0.00010 | $0.00242 |
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.
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 Conventions — Bash: 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
- Read
core/config/verification-checklist.md(framework checklist). - Read
core/config/verification-checklist-domain-specific.md(foundational domain checklist template — see file header for the three-tier loading explanation). - IF
world/verification-checklist.mdexists: 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)')"
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.
- 7d ago First seen · 186 lines · 101 tokens per session scan A 3a81ebf32241
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.
Other skills, from other repositories
interview-prep
Technical interview preparation expert for algorithms, system design, and behavioral questions.
agent-challenges
Agent skill for challenges - invoke with $agent-challenges.
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…
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…
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.
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…