completely:run

A task runner for a Beads queue, where Beads is the task-tracking system used by the workflow. It can execute tasks with human checkpoints or unattended fresh-agent sessions, while recording status and evidence.

In plain words
What is it for?
Use it to run ready tasks one at a time, choose supervised or unattended execution, apply test-driven development (writing tests around the change), run quality checks, and close completed tasks.
Why use it?
It removes the need to manually claim, verify, document, and close each queued task. It also marks blocked work instead of leaving incomplete tasks looking finished.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/23ag1/completely/run
Any agent
npx skills add 23ag1/completely --skill run
Clone the repo
git clone --depth 1 https://github.com/23ag1/completely

Made for: Claude Code, Codex.

Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 372 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00079 $0.00372
Opus 5 $0.00039 $0.00186
Sonnet 5 $0.00016 $0.00074
Haiku 4.5 $0.00008 $0.00037

Measured 2d ago against content hash c5ba7e3e317e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

completely:run 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 2d 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.

plugin/skills/run/SKILL.md · 22 lines

What it actually says

Execute planned work from Beads with the right autonomy level.

Pick the mode (the dial): run unattended only when the spec is unambiguous, tasks are atomic, write-zones are disjoint, and verification is automated. Otherwise run supervised.

  • Unattended (cmpl run / cmpl run --max N): fresh claude -p per iteration reading the Beads-aware overlay prompt; ONE task per iteration; stops when bd ready is empty. No --dangerously-skip-permissions — the guard hook + allowlist gate dangerous ops.
  • Supervised (cmpl run --mode supervised): hand off to /gsd:execute-phase <phase> (wave subagents, checkpoints). Either way, status lives in Beads and evidence in bd comment.

Use --dry-run first to see how many tasks are ready and what would execute, without running. Each iteration: claim one task → TDD → gates → evidence comment → bd close → next. Blocked → bd ... --status blocked + comment, never a silent stub.

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. 2d ago First seen · 22 lines · 79 tokens per session scan A c5ba7e3e317e

Subscribe to this mod's changes

completely:run is a skill published in the GitHub repository 23ag1/completely (5 stars, last pushed 2mo ago), licensed MIT. It adds 79 tokens to every session and 372 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 2026-08-31.

Related

Other skills, from other repositories