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 dandacompany/bluekiwi --skill bk-improvegit clone --depth 1 https://github.com/dandacompany/bluekiwiWrote 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/dandacompany/bluekiwi/bk-improve)<a href="https://agentmods.dev/skills/dandacompany/bluekiwi/bk-improve"><img src="https://agentmods.dev/badge/skills/dandacompany/bluekiwi/bk-improve/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/dandacompany/bluekiwi/bk-improve"><img src="https://agentmods.dev/badge/skills/dandacompany/bluekiwi/bk-improve.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 | $0.00067 | $0.02500 |
| Opus 5 | $0.00034 | $0.01250 |
| Sonnet 5 | $0.00013 | $0.00500 |
| Haiku 4.5 | $0.00007 | $0.00250 |
Grade A, and why
bk-improve 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 9d 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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Asking questions across runtimes: wherever this skill says
AskUserQuestion, use your host runtime's native structured-question tool:AskUserQuestion(Claude Code),clarify(Hermes Agent),requestUserInput(Codex CLI),question(opencode). Always present the choices through that tool rather than plain prose. If the runtime has no such tool, list the options as numbered text and wait for the user's reply before proceeding.
BlueKiwi Workflow Improve
Improve an existing workflow by creating a new version, then optionally execute it to compare results.
Which creation skill to use?
/bk-improve(this one) — a registered workflow exists and needs a better version./bk-create— start from a natural-language goal without an existing workflow./bk-import— external resource (GitHub repo, URL, local skill, pasted text) to convert into a new workflow.
Argument Handling
/bk-improve→ Fetch workflow list, ask user to select./bk-improve <workflow name>→ Load that workflow directly.
Execution Steps
Step 1: Select Target Workflow
If no argument, call list_workflows and ask via AskUserQuestion:
- header: "Which workflow?"
- "Which workflow would you like to improve?"
- options: workflow title list (up to 4)
Step 2: Understand Improvement Direction
Ask via AskUserQuestion:
- header: "Improvement goal"
- "What would you like to improve?"
- options: ["Set more quantitative goals", "Break steps into finer detail", "Improve accuracy", "Type my own"]
If "Type my own" → accept free-text improvement direction.
Step 3: Analyze the Current Workflow
Leveraging Feedback Data
When improving a workflow, call advance(peek=true) on a past task to check for feedback_data.
If feedback_data exists, use it as the primary input for improvement analysis:
- Read each feedback item's
questionandanswer - Identify negative responses (unsatisfied, insufficient, etc.)
- Prioritize steps related to that feedback for improvement
- Explicitly note "based on user feedback" when proposing changes
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.
- 9d ago First seen · 242 lines · 67 tokens per session scan A 58eccee8146f
bk-improve is a skill published in the GitHub repository dandacompany/bluekiwi (23 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 2,500 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.