completely:control

A controlled task runner for completing exactly one ready Beads task through a defined software-development process. Beads is a task-tracking system for coding work.

In plain words
What is it for?
Use it to claim one task, map the codebase, plan and implement changes, run tests and checks, use reviewers and debugging when needed, commit the result, and close the task only after acceptance.
Why use it?
It keeps the work visible and ordered by requiring understanding, planning, implementation, tests, reviews, verification, and a human pause when approval is needed.

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

Made for: Claude Code, Codex.

Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 366 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 $0.00092 $0.00366
Opus 5 $0.00046 $0.00183
Sonnet 5 $0.00018 $0.00073
Haiku 4.5 $0.00009 $0.00037

Measured yesterday against content hash 28998a60a1d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

completely:control 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 yesterday.

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/control/SKILL.md · 22 lines

What it actually says

Execute the single next bd ready task — exactly ONE — through the full task engine (core/task-engine.md), in this session, with maximum observation and control.

Follow steps 0–10 of the engine for that one task: claim → understand (spawn gsd-codebase-mapper / gsd-phase-researcher as needed) → plan-check (goal-backward) → decompose & spawn subagents in parallel where write-zones are disjoint (serialize with bd merge-slot) → TDD + craft skills → cmpl check + cmpl lint → spawn code-reviewer + security-reviewer → gsd-verifier + the default-FAIL evaluator → gsd-debugger on repeated failure → LAND: bd comment evidence → git commit (confirm it landed) → ONLY THEN bd close if the evaluator ACCEPTED.

Show me each subagent's result. PAUSE at any human gate (checkpoint) and at STOP-conditions. After the one task lands, STOP and report — I decide whether to run the next.

Identical to one iteration of /completely:auto — same full engine — just observed and one-at-a-time. Nothing is reduced.

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. yesterday First seen · 22 lines · 92 tokens per session scan A 28998a60a1d6

Subscribe to this mod's changes

completely:control is a skill published in the GitHub repository 23ag1/completely (5 stars, last pushed 2mo ago), licensed MIT. It adds 92 tokens to every session and 366 once invoked, about $0.0005 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