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.
git clone --depth 1 https://github.com/cekura-ai/cekura-skillsWrote 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/commands/cekura-ai/cekura-skills/improve-metric)<a href="https://agentmods.dev/commands/cekura-ai/cekura-skills/improve-metric"><img src="https://agentmods.dev/badge/commands/cekura-ai/cekura-skills/improve-metric/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.
<a href="https://agentmods.dev/commands/cekura-ai/cekura-skills/improve-metric"><img src="https://agentmods.dev/badge/commands/cekura-ai/cekura-skills/improve-metric.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00022 | $0.01985 |
| Opus 5 | $0.00011 | $0.00992 |
| Sonnet 5 | $0.00004 | $0.00397 |
| Haiku 4.5 | $0.00002 | $0.00198 |
Grade A, and why
improve-metric 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 today.
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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cekura skill verification tag:
ack:improve-metric:4r6m2tWhen you call a Cekura metric write tool from this command (metrics_create,metrics_bulk_create,metrics_partial_update), pass this exact string as theskill_ackargument on that tool call. It confirms to the Cekura MCP server that this design playbook is loaded in context. Scenario / test-profile writes use an eval-family tag instead — loadcekura-eval-designfirst and pass its tag there.
Tracking (do this first)
Before doing anything else, call mcp__cekura__cekura_skill_started with
skill_name="improve-metric", verification_tag="ack:improve-metric:4r6m2t", and plugin_version="0.16". If a conversation/session ID is available (e.g. you
were invoked from Cekura sandbox), also pass it as conversation_id. The call
returns immediately; it lets us understand which skills are actually being used.
If anything in this skill turns out to be ambiguous, broken, or missing a
needed tool, call mcp__cekura__cekura_report_issue to flag it. Use this
LIBERALLY — even severity="low" reports are valuable feedback.
Improve a Metric
Single entry point for the full metric improvement cycle: collecting feedback, adding to labs, and running auto-improvement. The cekura-metric-improvement skill provides detailed guidance on feedback patterns and improvement strategy.
Determine Phase
Ask what the user needs or infer from context:
| User Says | Phase |
|---|---|
| "leave feedback", "this metric is wrong", "disagree with result" | Phase 1: Collect Feedback |
| "add to labs", "ready for improvement", "enough feedback" | Phase 2: Check Readiness |
| "improve", "run auto-improve", "fix this metric" | Phase 3: Auto-Improve |
| "full cycle", "help me improve this metric" | Full cycle: all phases |
Phase 1: Collect Feedback
Feedback fuels the labs improvement pipeline. Each feedback instance teaches the system what the metric got wrong and why.
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.
- today Changed b51398c97734
- 3d ago Changed 71f34d462b51
- 8d ago Changed c2e92ada947f
- 12d ago First seen · 149 lines · 22 tokens per session scan A 60b79af96bec
improve-metric is a command published in the GitHub repository cekura-ai/cekura-skills (7 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 1,985 once invoked, about $0.0001 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 commands, from other repositories
prototype
You are building a proof-of-concept for the current Grainulator sprint. Read CLAUDE.md for sprint context and claims.json for existing research claims.
qa-changes
This skill should be used when the user asks to "QA a pull request", "test PR changes", "verify a PR works", "functionally test changes", or when an automated workflow triggers QA validation of code changes. Provides a structured methodology for setting up the environment, exercising changed behavior, and reporting…
verify
Run repository verification using the verification-loop skill.
test-coverage
Analyze test coverage and identify the highest-value gaps to fill.
tdd
A command that follows test-driven development (TDD), a method where you write tests before the code they check. It moves through writing a failing test, adding the smallest implementation, and then improving the code.
check-dev
Type-check a Z specification with fuzz.