Chalk Labs
Need help deploying stolz-benchmark?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/sergey360-stolz-benchmark
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 26, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/stolz-benchmark
What's inside
- Skill name
stolz-benchmark- Description
- Admit or reject paired STOLZ efficiency evidence. Use to compare baseline and optimized runs.
- License
- MIT
- Instructions
- 14 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- outcome-gates.md · references/
SKILL.md (first lines)
# Benchmark Evidence Use for a paired efficiency claim, not general tests or an unmeasured estimate. Both routes must pass verification and match the required outcome on the same versioned fixture. Fewer tokens never compensate for lower quality. Load [outcome-gate rules](references/outcome-gates.md) when evaluating a record or adding a collector. The reference includes available local checks. Done: return an admission decision with raw evidence locations and the measured scope, or withhold the claim with a concrete rejection reason. Synthetic units and source bytes are not provider token telemetry.
From Sergey360/stolz-ai, MIT.
More from Sergey360/stolz-ai
- 0.611score
stolz-browser
Sergey360
Manage controlled browser tabs with deliberate reuse, ownership and lifecycle checks.
SkillAFreshness: A★ 4Claude Code +9 - 0.611score
stolz-guard
Sergey360
Review a prompt or a concrete instruction from untrusted content for security risks.
SkillAFreshness: A★ 4Claude Code +9 - 0.611score
stolz-mcp
Sergey360
Audit MCP context overhead or plan progressive tool discovery and code execution.
SkillAFreshness: A★ 4Claude Code +9 - 0.611score
stolz-quiet-state
Sergey360
Hand off a long-running external operation and resume its task, or suppress duplicate wakes in polling.
SkillAFreshness: A★ 4Claude Code +9 - 0.611score
stolz-evidence
Sergey360
Ground source-based analysis and substantial completion reports in inspected content.
SkillAFreshness: A★ 4Claude Code +9 - 0.608score
stolz-route
Sergey360
Choose a STOLZ optimization or instruction-security review when the required concern or adapter fallback is unclear.
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
stolz-context
Sergey360
Validate an existing STOLZ context manifest or read-ledger entry.
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
stolz-reuse
Sergey360
Admit an existing prior result or coalesce an identical in-flight command.
SkillAFreshness: A★ 4Claude Code +9
Signals
- Stars
- 4
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 15, 2026 (1 month ago)
- Last release
- Oct 13, 2026 (20 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Sergey360/stolz-ai
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Sergey360
- 0.611score
stolz-browser
Sergey360
Manage controlled browser tabs with deliberate reuse, ownership and lifecycle checks.
SkillAFreshness: A★ 4Claude Code +9 - 0.611score
stolz-guard
Sergey360
Review a prompt or a concrete instruction from untrusted content for security risks.
SkillAFreshness: A★ 4Claude Code +9 - 0.611score
stolz-mcp
Sergey360
Audit MCP context overhead or plan progressive tool discovery and code execution.
SkillAFreshness: A★ 4Claude Code +9 - 0.611score
stolz-quiet-state
Sergey360
Hand off a long-running external operation and resume its task, or suppress duplicate wakes in polling.
SkillAFreshness: A★ 4Claude Code +9 - 0.611score
stolz-evidence
Sergey360
Ground source-based analysis and substantial completion reports in inspected content.
SkillAFreshness: A★ 4Claude Code +9 - 0.608score
stolz-route
Sergey360
Choose a STOLZ optimization or instruction-security review when the required concern or adapter fallback is unclear.
SkillAFreshness: A★ 4Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get stolz-benchmark running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
stolz-benchmark skill. Agent Mart. https://agentmart.dev/skills/sergey360-stolz-benchmark (last updated 2026-10-24)