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/upgrade-skills)<a href="https://agentmods.dev/commands/cekura-ai/cekura-skills/upgrade-skills"><img src="https://agentmods.dev/badge/commands/cekura-ai/cekura-skills/upgrade-skills/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/upgrade-skills"><img src="https://agentmods.dev/badge/commands/cekura-ai/cekura-skills/upgrade-skills.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 | $0.00016 | $0.00983 |
| Opus 5 | $0.00008 | $0.00491 |
| Sonnet 5 | $0.00003 | $0.00197 |
| Haiku 4.5 | $0.00002 | $0.00098 |
Grade A, and why
upgrade-skills 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 12d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tracking (do this first)
Before doing anything else, call mcp__cekura__cekura_skill_started with
skill_name="upgrade-skills". 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.
Upgrade the Cekura plugin to the latest published version.
In Claude Code CLI, a
SessionStarthook auto-runs the re-pin commands below on every launch, so most CLI users are already current. (Claude Desktop uses a separate plugin store with its own update setting — the hook doesn't reach it; update there from the Desktop plugin panel.) Run this command to force an upgrade now (mid-session), or to handle the stale-layout cohort the hook can't fix.
Process
1. Re-pin the plugin to the latest version (this is the actual upgrade)
Run both CLI commands. The first refreshes the marketplace catalog from GitHub; the second moves the installed version pin to the latest. A plain git pull of the marketplace checkout does not move the pin — which is why sessions can keep loading an old version after a "successful" pull. These commands do move it.
claude plugin marketplace update cekura-skills
claude plugin update cekura@cekura-skills
If either command errors:
- Network / auth: check internet access and GitHub credentials, then retry.
Source path does not existor the update is a no-op while the version is clearly behind: this is the stale-layout case — jump to step 3.
2. Apply it in the current session
Tell the user to run /reload-plugins — it hot-reloads the newly pinned version with no restart in the common case. If /reload-plugins warns about an MCP cache invalidation, a restart (or /reload-plugins --force) applies it. /reload-plugins only reloads what's already pinned on disk, so it must run after step 1, not instead of it.
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.
- 12d ago First seen · 84 lines · 16 tokens per session scan A cfad4f9984b9
upgrade-skills is a command published in the GitHub repository cekura-ai/cekura-skills (7 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 983 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.