Skip to content
cccskills
FreePublished on GitHub

beads-priority-assignment

Choose Beads issue priority (P0–P4, numeric, or named) from urgency, impact, and risk when creating or triaging work.

The English summary is being prepared. Showing the original description.

See how to install

Files included (1)

  • SKILL.md3.1 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

beads-priority-assignment

Use this skill whenever you bd create a issue or re-triage priority (bd update) so the queue reflects real severity. Follow bd doctor / your Beads version for the exact --priority values your CLI accepts (integers 0–4, labels like P0–P4, and/or names like critical / high / medium / low).

Harness mapping (dashboard + types/beads.ts)

Exports and the dashboard normalize numeric priority roughly as:

TierTypical bd inputsMeaning in this harness
Critical0, P0, criticalDrop other work: production down, active exploit, data loss, irreversible customer harm
High1, P1, highUrgent: broken main path, release blocker, failing CI on default branch, severe bug with weak workaround
Medium2, P2, mediumDefault scheduled work: most features, typical bugs, refactors with agreed dates
Low3–4, P3–P4, lowBacklog: polish, nice-to-have, cleanup, research spikes with no near deadline

Values 3 and above both map to low in the static dashboard export — use them to order work inside the backlog if your bd install preserves numeric order.

Rubric (three axes)

Score mentally; the highest axis that applies usually wins (then downgrade one step if mitigations exist).

  1. Urgency — Must this start today / this week / this sprint / later?
  2. Impact — How many users or systems are affected, and how badly?
  3. Risk if deferred — Does waiting increase security exposure, compliance exposure, cost, or cascade blockers?

Escalate one level if the issue blocks other ready work or sits on a critical path to a dated epic.

De-escalate one level if there is a documented workaround, the area is feature-flagged off, or the report is duplicate / unclear until clarified.

Defaults

  • If the user states “P0” / “urgent” / “critical”, map to that tier — do not normalize down.
  • If you have no signal after the rubric, use P2 / 2 / medium (harness default), not empty priority.
  • Never inflate priority to look important; never leave priority unset on purpose when the CLI supports it.

Examples

SituationSuggested priority
Auth service returning 500 for all logins0 / P0 / critical
CI red on master, no merge until fixed1 / P1 / high
New feature from roadmap, normal sprint2 / P2 / medium
Typo in internal-only docs3 or 4 / low
/triage auto-filed “CI failing on PR #n” (matches existing harness command)1 / P1 / high

Commands (non-interactive)

bd create --type task --title "[<repo>] ..." --priority <value>
bd update <id> --priority <value>

After changing priority on an existing issue, add a short Beads comment: worklog: priority set to <value> because <one line>.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Capture free-text work as a tracked Beads issue. Use when the user runs /add-bead or wants to quickly file a Beads issue.

The English summary is being prepared. Showing the original description.

jupes/agent-forge-harness2Updated Oct 19, 2026

Register a new sub-repo in the knowledge base.

The English summary is being prepared. Showing the original description.

jupes/agent-forge-harness2Updated Oct 19, 2026

Add focused Bun unit tests for mission-critical behavior and edge cases — not blanket coverage.

The English summary is being prepared. Showing the original description.

jupes/agent-forge-harness2Updated Oct 19, 2026

ask

Free

Answer questions about the codebase from knowledge files. Use when the user runs /ask or asks a domain/knowledge question about the repos.

The English summary is being prepared. Showing the original description.

jupes/agent-forge-harness2Updated Oct 19, 2026

Meta-skill for creating Agent Forge skills under .claude/skills/ with SKILL.md, optional references/ and scripts/, and Bun scaffolds. Use when the user wants to add or author a skill, scaffold a new skill folder, or align skill docs with harness conventions (JSON script output, Beads for tasks).

The English summary is being prepared. Showing the original description.

jupes/agent-forge-harness2Updated Oct 19, 2026

Ultra-compressed communication mode that preserves technical accuracy while dropping filler. Use when the user explicitly says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.

The English summary is being prepared. Showing the original description.

jupes/agent-forge-harness2Updated Oct 19, 2026

See all skills by jupes

Report a problem with this skill