mcp-contrast: Skill for Claude Code

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

bead-workflow is a skill for Claude Code from Contrast-Security-OSS/mcp-contrast. It costs 73 tokens per session (1,962 once invoked), scanned A, original, Apache-2.0.

A workflow for managing Beads, the repository's working issue tracker, through their full lifecycle. It covers creating, claiming, implementing, updating, triaging, commenting on, and closing issues.

In plain words
What is it for?
Use it to create or update issues, claim work, manage stacked branches, add comments and labels, and close completed work after committing it.
Why use it?
It keeps issue records consistent with repository rules, branch practices, commits, labels, and synchronization requirements.

Skill for Claude Code

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

This is Contrast-Security-OSS/mcp-contrast's own configuration. It tells Claude Code how to work on mcp-contrast 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 mcp-contrast configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Contrast-Security-OSS/mcp-contrast. 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/Contrast-Security-OSS/mcp-contrast/main/.claude/skills/bead-workflow/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Contrast-Security-OSS/mcp-contrast

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 bead-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/contrast-security-oss/mcp-contrast/bead-workflow/github.svg)](https://agentmods.dev/skills/contrast-security-oss/mcp-contrast/bead-workflow)
Your own site
<a href="https://agentmods.dev/skills/contrast-security-oss/mcp-contrast/bead-workflow"><img src="https://agentmods.dev/badge/skills/contrast-security-oss/mcp-contrast/bead-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 bead-workflow

Your own site · 80×15
<a href="https://agentmods.dev/skills/contrast-security-oss/mcp-contrast/bead-workflow"><img src="https://agentmods.dev/badge/skills/contrast-security-oss/mcp-contrast/bead-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,962 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: 1 finding, up to medium

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 →

  • medium Excessive Agency · line 26
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 $0.00073 $0.01962
Opus 5 $0.00036 $0.00981
Sonnet 5 $0.00015 $0.00392
Haiku 4.5 $0.00007 $0.00196

Measured 9d ago against content hash dc725de3eb04, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

bead-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/bead-workflow/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bead Workflow

Beads (br) is the working issue store. This skill governs every bead mutation, create, claim, implement, close, triage, and comment. For read-only commands (br show, br ready, br list) this skill does not need to be loaded.

For Jira ticket creation, bead-to-Jira parity rules, and post-merge transitions, invoke the jira-workflow skill. This skill does not duplicate those rules.

Public repo note. This repository is public. .beads/ is gitignored and must stay that way, bead content is internal. Never commit anything under .beads/, and never quote internal-only detail from beads into committed files.

1. Creating a bead

br create "Title" --type <type> --priority <0-4> --description "..." \
  --labels "repo:mcp-contrast" [--parent <parent-id>]

Required fields:

  • --type: task, bug, feature, epic, chore, docs, question. Use your judgment based on context. Epics are typically parent beads with children, matching how Jira epics work.
  • --priority: Default to P2 (medium) unless context clearly indicates otherwise. P0/P1 for blocking issues, P3/P4 for nice-to-haves and backlog.

Repo label (repo:<name>): Apply a repo: label for the repo where the code work will happen (normally repo:mcp-contrast). Work that spans repos can carry multiple repo: labels. If the target repo changes later, update the label. Figure the repo out from context, do not ask the user.

Multi-line content: quoted heredocs prevent shell interpretation.

br create "Title" --description "$(cat << 'EOF'
Markdown with `code`, --flags, and $(vars), all literal.
EOF
)"

For the design field, always use scripts/br-set-design <bead-id> <file-path> (the CLI misparses -- in markdown).

Parent-child relationships: Use --parent <parent-id> when creating a child bead. Child beads work on the same branch as their parent. If the parent has a Jira ticket and the user wants one for the child, follow the jira-workflow skill (Story under Epic when the parent ticket is an Epic, otherwise ask). Only create Jira tickets when the user explicitly requests it.

Read the full file on GitHub · 124 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 · 124 lines · 73 tokens per session scan A dc725de3eb04

Subscribe to this mod's changes

bead-workflow is a skill published in the GitHub repository Contrast-Security-OSS/mcp-contrast (23 stars, last pushed 4d ago), licensed Apache-2.0. It adds 73 tokens to every session and 1,962 once invoked, about $0.0004 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.