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 skills add cekura-ai/cekura-skills --skill cekura-bot-test-writergit 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/skills/cekura-ai/cekura-skills/cekura-bot-test-writer)<a href="https://agentmods.dev/skills/cekura-ai/cekura-skills/cekura-bot-test-writer"><img src="https://agentmods.dev/badge/skills/cekura-ai/cekura-skills/cekura-bot-test-writer/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/skills/cekura-ai/cekura-skills/cekura-bot-test-writer"><img src="https://agentmods.dev/badge/skills/cekura-ai/cekura-skills/cekura-bot-test-writer.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 | $0.00172 | $0.03644 |
| Opus 5.5 | $0.00069 | $0.01458 |
| Sonnet 5.5 | $0.00034 | $0.00729 |
| Haiku 4.5 | $0.00017 | $0.00364 |
Grade A, and why
cekura-bot-test-writer 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 15d 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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Before taking any action, call mcp__cekura__cekura_skill_started with skill_name="cekura-bot-test-writer", verification_tag="ack:cekura-bot-test-writer:3d7k2m", and plugin_version="0.19". It returns immediately and lets Cekura see which skills are in use.
Cekura Bot Test Writer
Purpose
Keep a repository's committed Cekura suite in step with the bot it tests, one pull request at a time. The unit of work is a diff, not a repository: read what changed, decide whether the existing cases already prove it, and make the smallest edit that closes a genuine gap.
The suite is source code with a history. Its value comes from cases whose keys and meanings hold still across commits, so a red today is comparable to a green last month. An updater that regenerates, renames, reflows, or grows the file every time it runs destroys exactly that.
Where this skill sits
| Situation | Skill |
|---|---|
| The repository has no committed suite yet | cekura-infra-test-suite — creation, coverage matrix, CI wiring |
| A suite exists and a PR changed the agent | this skill |
| Dashboard evaluators, adaptive or exploratory scenarios | cekura-eval-design |
| Production calls are failing and need reproducing | cekura-flag-call-log-failures → cekura-generate-scenarios |
| A failure needs a fix, not just a test | cekura-self-improving-agent |
If Step 0 finds no suite, stop and hand over to cekura-infra-test-suite. Do not invent one
inside someone's pull request: a suite authored mid-review has no baseline, so its first run is
unreadable — nobody can tell a real regression from a case that was never right.
The default answer is "no change"
Most pull requests do not change anything a caller can hear. Refactors, logging, type hints, dependency bumps, internal renames, tests, docs and CI all normally end at no change, and saying so with evidence is a complete, correct result — not a lazy one.
A suite that gains a case per pull request stops being a gate. Every case is a live call: it costs credit on every run, adds wall-clock to every merge, and one more flake-prone red that reviewers learn to wave through. The cheapest edit that closes the gap is the right one, and the cheapest edit is usually none. Produce the decision table either way — the reasoning is the deliverable when the file does not change.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 15d ago Changed 6bb830f761a4
- 22d ago Changed cbf335ebe2f9
- 1mo ago Changed 5dd252a5ea5b
- 1mo ago Changed 81a893d8eaa5
- 1mo ago Changed f2906cf54580
- 1mo ago First seen · 264 lines · 172 tokens per session scan A 51c9328ee4b8
cekura-bot-test-writer is a skill published in the GitHub repository cekura-ai/cekura-skills (8 stars, last pushed today), licensed MIT. It adds 172 tokens to every session and 3,644 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-09-11.
Other skills, from other repositories
adk-go-self-review
Review an ADK Go change the way a maintainer will — a fresh-context pass over the whole diff, five lenses (correctness and tests, scope, simplicity, style, adk-python parity), and the mutation check that proves your tests pin the change. Use before opening a PR, before any later push that changes code, and when asked…
adversarial-reviewer
Stress-test a code change for concrete correctness defects, unsafe assumptions, and failure modes. Use when the user explicitly asks for an adversarial review, a deep bug hunt, or to tear a change apart, or to check your own change before submitting it. Do not use for ordinary review, style feedback, or general…
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
semgrep-rule-variant-creator
Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages as input, produces independent rule+test directories for each language.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
plugin-review
Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.