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 agentmods add skills/karanb192/claude-code-hooks/leaderboardnpx skills add karanb192/claude-code-hooks --skill leaderboardgit clone --depth 1 https://github.com/karanb192/claude-code-hooksWrote 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/karanb192/claude-code-hooks/leaderboard)<a href="https://agentmods.dev/skills/karanb192/claude-code-hooks/leaderboard"><img src="https://agentmods.dev/badge/skills/karanb192/claude-code-hooks/leaderboard.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 | $0.00020 | $0.00199 |
| Opus 5 | $0.00010 | $0.00100 |
| Sonnet 5 | $0.00004 | $0.00040 |
| Haiku 4.5 | $0.00002 | $0.00020 |
Grade B, and why
leaderboard scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
Keep it short; do not re-run any commands. What it actually says
Context-cost leaderboard
!node "${CLAUDE_SKILL_DIR}/../../context-hogs.js" --render 2>/dev/null || node "${CLAUDE_PLUGIN_ROOT}/context-hogs.js" --render
The table above is this repository's most token-expensive files, aggregated across
your recent sessions (read count, cumulative tokens, estimated cost). It is produced
by the context-hogs hook, which records as you work.
Briefly call out the top 1-3 offenders and suggest one concrete fix each: for
example: split an oversized file, exclude a generated/vendored path, or add the
suggested CLAUDE.md / permissions.deny block for a file Claude keeps re-reading.
Keep it short; do not re-run any commands.
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.
- 4d ago First seen · 19 lines · 0 tokens per session scan B 381f3364aa9b
leaderboard is a skill published in the GitHub repository karanb192/claude-code-hooks (498 stars, last pushed 11d ago), licensed MIT. It adds 20 tokens to every session and 199 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
system-audit
Periodic evidence-based self-audit of the whole agent system — the orchestrator, its docs/SSOTs, rules, memory, subagents, tools, infra and the work it claims to have delivered — followed by immediate cheap-safe fixes and a ranked backlog. Use when the user says 'аудит системы', 'проверь себя', 'самопроверка', 'system…
session-review
End-of-session adversarial review loop. Assemble the session's work into a role-assigned, self-contained brief, then run independent reviewers in parallel — an isolated code-reader (the idea-validator agent) that reads the ACTUAL files and web-checks technology currency, plus an external-family model if you have one …
close-session
End-of-session ritual — audit today's patterns against accumulated memory, propose promotions, refresh MEMORY.md, and write the session handoff. Use when the user says "/memory-kit:close-session", "закрой сессию", "закрываем", "we're done for today", "wrap up".
memory-audit
Audit MEMORY.md against the memory discipline — oversized sections, settled multi-session patterns that belong in knowledge/concepts/, stacked chronicle blocks, stale entries. Produces a move plan as a table for approval, then executes the approved moves atomically. Use when the SessionStart hook reports a tripped…
second-opinion
Cross-check the agent's own answer with independent reviewers before bringing it to the user. Use when the user says 'second opinion', 'sanity check', 'cross-check', 'am I missing something', 'stress-test', 'devil's advocate', 'run a full review', 'this is important', 'high-stakes', 'help me choose between', 'critique…
qa-sweep
Run a multi-lens agent QA sweep of the RUNNING product: spawn qa agents (one per lens — user-flow · edge-state · honesty · contract · ux-critique), collect their structured findings, integrator-verify the load-bearing ones, and land verified findings as backlog tickets + a run record in the project's qa/ folder. Use…