nubecita: Skill for Claude Code

.claude/skills/bd-workflow/SKILL.md

bd-workflow is a skill for Claude Code from kikin81/nubecita. It costs 118 tokens per session (5,579 once invoked), scanned A, original, MIT.

A workflow for managing Beads tasks, where Beads is a task-tracking system used in this repository.

In plain words
What is it for?
It helps claim a task, create a correctly named branch, finish the work in a pull request, and handle standalone tasks or tasks belonging to a larger epic.
Why use it?
It handles the repeated branch, commit, pull-request, and issue-relationship steps that can otherwise be easy to miss.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is kikin81/nubecita's own configuration. It tells Claude Code how to work on nubecita itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything nubecita configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kikin81/nubecita. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/kikin81/nubecita/main/.claude/skills/bd-workflow/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/kikin81/nubecita

Made for: Claude Code.

Wrote 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.

agentmods badge for bd-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/kikin81/nubecita/bd-workflow/github.svg)](https://agentmods.dev/skills/kikin81/nubecita/bd-workflow)
Your own site
<a href="https://agentmods.dev/skills/kikin81/nubecita/bd-workflow"><img src="https://agentmods.dev/badge/skills/kikin81/nubecita/bd-workflow/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.

agentmods 80×15 button for bd-workflow

Your own site · 80×15
<a href="https://agentmods.dev/skills/kikin81/nubecita/bd-workflow"><img src="https://agentmods.dev/badge/skills/kikin81/nubecita/bd-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,579 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Tool Misuse · line 103
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • high Tool Misuse · line 287
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00118 $0.05579
Opus 5 $0.00059 $0.02789
Sonnet 5 $0.00024 $0.01116
Haiku 4.5 $0.00012 $0.00558

Measured 9d ago against content hash 69015999e50e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

bd-workflow 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.

.claude/skills/bd-workflow/SKILL.md · 306 lines

How it starts

The opening of the file, as written. The whole thing — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Automate the bd-driven branch/commit/PR ceremony documented in CLAUDE.md's Workflow section. Three flows: start (claim + branch), finish (push + PR), and land (merge an epic's stack). Never close the bd issue here — closure happens after merge.

Two landing paths

The bd issue's shape picks the path. Determine it in the start flow and carry it through:

  • Standalone issue (no epic parent) → one branch, one PR to main, squash-merge. Unchanged from before.
  • Child of an epic → one branch and one PR in the epic's gh stack, stacked on main. Nothing merges until the whole epic lands via gh stack merge, so the epic cuts exactly one semantic release.

Detect in two steps. parent is a bare id string ("nubecita-1fy"), not a nested object, so the parent's type needs its own lookup — a non-empty parent alone does not mean the issue is an epic child:

parent=$(bd show <id> --json | jq -r '.[0].parent // empty')
if [ -n "$parent" ]; then
  bd show "$parent" --json | jq -r '.[0].issue_type'
fi

Use the if form, not [ -n "$parent" ] && …. The && chain exits 1 when parent is empty, and "this issue has no parent" is a normal, expected outcome — under set -e, or in an agent harness that surfaces non-zero exit as a tool failure, the standalone path would look like an error every time.

epic → stacked path. Empty parent, or a parent of any other type → standalone path. If the repo has no stack yet for that epic, the start flow creates it.

When to use

  • Start flow — user asks to begin work on a bd id: "start nubecita-aew", "let's pick up ", "claim this one".
  • Finish flow — user is done committing and wants to push/open a PR: "open the PR", "ship it", "finish this task".
  • Land flow — an epic's stack is complete and green: "land the stack", "merge the epic", "ship the feature".

If the user has not chosen a bd id yet, run bd ready and offer the top candidates before starting.

Start flow

Read the full file on GitHub · 306 lines

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.

  1. 9d ago First seen · 306 lines · 118 tokens per session scan A 69015999e50e

Subscribe to this mod's changes

bd-workflow is a skill published in the GitHub repository kikin81/nubecita (5 stars, last pushed yesterday), licensed MIT. It adds 118 tokens to every session and 5,579 once invoked, about $0.0006 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.