task-direction-approval

A decision rule for cases where the requested tool, library, architecture, or automation approach may need to change.

In plain words
What is it for?
Use it when replacing a library, changing architecture, or using a manual workaround, so the available approaches and their risks are agreed first.
Why use it?
It explains the cause of the problem and makes the trade-offs clear before changing direction. Work does not switch to an alternative until the user chooses an option.

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/kasuken/github-copilot-superpowers/task-direction-approval
Any agent
npx skills add kasuken/github-copilot-superpowers --skill task-direction-approval
Clone the repo
git clone --depth 1 https://github.com/kasuken/github-copilot-superpowers

Made for: Claude Code, Codex.

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 309 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 $0.00043 $0.00309
Opus 5 $0.00022 $0.00154
Sonnet 5 $0.00009 $0.00062
Haiku 4.5 $0.00004 $0.00031

Measured 2d ago against content hash 1255ec6e754e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-direction-approval 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.

.github/skills/task-direction-approval/SKILL.md · 47 lines

What it actually says

Task Direction Approval

Overview

This skill prevents unauthorized direction changes by forcing explicit user consent before deviating from the original requirements.

Use when...

  • Switching from the original tech/library to alternatives
  • Replacing an automated approach with a manual workaround
  • Changing architecture or design patterns
  • Delivering different results than requested

Symptoms / keywords

  • “can’t use X”, “let’s switch to Y”, “workaround”, “manual”, “different approach”, “alternative library”, “rewrite”, “change architecture”

Communication protocol (template)

❌ Wrong Response:

"GraphQL Codegen failed, so I'll define types manually instead."

✅ Correct Response:

"GraphQL Codegen failed due to authentication error. Options available:

  1. Add authentication headers
  2. Try different endpoint
  3. Download schema file directly Which approach would you prefer?"

Minimal workflow

  1. Explain the failure root cause clearly (what failed, why it failed, evidence).
  2. Present 2-3 viable options with trade-offs (speed, risk, maintenance, correctness).
  3. Ask for explicit user choice.
  4. Only proceed after approval.

Notes

  • Use investigation-mode when there are repeated failures or the situation is unclear.
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 · 47 lines · 43 tokens per session scan A 1255ec6e754e

Subscribe to this mod's changes

task-direction-approval is a skill published in the GitHub repository kasuken/github-copilot-superpowers (16 stars, last pushed 6mo ago), licensed MIT. It adds 43 tokens to every session and 309 once invoked, about $0.0002 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.