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.
npx agentmods add skills/kasuken/github-copilot-superpowers/task-direction-approvalnpx skills add kasuken/github-copilot-superpowers --skill task-direction-approvalgit clone --depth 1 https://github.com/kasuken/github-copilot-superpowersWhat 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.
| Model | Per session | Once 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 |
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.
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:
- Add authentication headers
- Try different endpoint
- Download schema file directly Which approach would you prefer?"
Minimal workflow
- Explain the failure root cause clearly (what failed, why it failed, evidence).
- Present 2-3 viable options with trade-offs (speed, risk, maintenance, correctness).
- Ask for explicit user choice.
- Only proceed after approval.
Notes
- Use
investigation-modewhen there are repeated failures or the situation is unclear.
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.
- 2d ago First seen · 47 lines · 43 tokens per session scan A 1255ec6e754e
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.
Other skills, from other repositories
maintenance-create-ticket-on-jira
Create or update a Jira ticket for a workload maintenance upgrade, based on maintenance upgrade check files.
jenkins-cli
Perform Jenkins operations using the jenkins-cli.
maintenance-check-aws-eks
Check everything that can be upgraded for maintenance across an AWS EKS Kubernetes cluster and output a decision file with Jira-formatted tickets for any required upgrades.
create-terraform-helm-upgrade-plan
Create a detailed upgrade plan for a Helm release managed by Terraform, comparing the current and desired chart versions including breaking changes and required code changes.
code-review
Analyze code changes between two local Git branches and perform a comprehensive code review. Use ONLY for local git branch comparisons. Do NOT use when a GitLab or GitHub MR/PR URL or MR ID is provided — use gitlab-cli or github-cli skill instead.
commit-code
Analyze code changes to prepare conventional commit message and commit to a new branch.