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 skills add brunob54/superpowers-orchestrator --skill deliberationgit clone --depth 1 https://github.com/brunob54/superpowers-orchestratorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/brunob54/superpowers-orchestrator/deliberation)<a href="https://agentmods.dev/skills/brunob54/superpowers-orchestrator/deliberation"><img src="https://agentmods.dev/badge/skills/brunob54/superpowers-orchestrator/deliberation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/brunob54/superpowers-orchestrator/deliberation"><img src="https://agentmods.dev/badge/skills/brunob54/superpowers-orchestrator/deliberation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00126 | $0.01071 |
| Opus 5 | $0.00063 | $0.00535 |
| Sonnet 5 | $0.00025 | $0.00214 |
| Haiku 4.5 | $0.00013 | $0.00107 |
Grade A, and why
deliberation 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deliberation
Surface genuine tension in a decision before committing to a direction.
When to use
Some decisions get worse when you're forced to choose too early. Use deliberation when:
- The options themselves are not yet well-defined
- The problem may be framed incorrectly (the real question hasn't been asked)
- Multiple legitimate constraints pull in different directions
- Brainstorming feels premature — there's no clear "right shape" for the solution yet
Do not use for: decisions that are already well-framed with clear options. Those go directly to brainstorming. Deliberation is for when you're not yet ready for options.
Procedure
1. Name the decision
State the decision being deliberated in one sentence. Be precise — a vague decision produces vague perspectives.
Example: "Should we migrate the authentication layer from JWT to session cookies?"
2. Identify 3–5 genuine stakeholder perspectives
Choose perspectives that have real, distinct stakes in the decision. Each perspective represents a legitimate set of constraints or values — not a person, but a role with a coherent viewpoint.
Good perspectives for technical decisions:
- The Security Engineer — attack surface, credential management, audit trail
- The Developer Experience Advocate — implementation complexity, debugging, onboarding
- The Ops/Infrastructure Engineer — deployment, scaling, observability, failure modes
- The Maintainability Advocate — long-term code health, testability, cognitive load
- The Performance Engineer — latency, throughput, caching, resource cost
- The User/Product Perspective — visible user impact, reliability, behaviour changes
Choose only perspectives with genuine stakes in this specific decision. Three well-chosen perspectives beat five generic ones.
3. Let each perspective speak once
For each perspective in turn:
- State what this perspective most values in the context of this decision
- Identify the specific concern or constraint it sees
- Name what it would lose in each direction being considered
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.
- 9d ago First seen · 114 lines · 126 tokens per session scan A 84412df38a0d
deliberation is a skill published in the GitHub repository brunob54/superpowers-orchestrator (3 stars, last pushed 3d ago), licensed MIT. It adds 126 tokens to every session and 1,071 once invoked, about $0.0006 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.
Other skills, from other repositories
github-pr-review
Handles PR review comments and feedback resolution. Use when user wants to resolve PR comments, handle review feedback, fix review comments, address PR review, check review status, respond to reviewer, verify PR readiness, review PR comments, analyze review feedback, evaluate PR comments, assess review suggestions, or…
privacy-guard
Prevents private infrastructure details (node hostnames, internal project names, local usernames and personal emails, absolute home paths, private and VPN IP ranges) from leaking into public repositories through commits, PRs, docs or release artifacts. Use when working in a public or soon-to-be-public repo, before…
github-pr-creation
Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…
github-pr-merge
Merges GitHub Pull Requests after validating pre-merge checklist. Use when user wants to merge PR, close PR, finalize PR, complete merge, approve and merge, or execute merge. Runs pre-merge validation (tests, lint, CI, comments), confirms with user, merges with proper format, handles post-merge cleanup.
git-commit
Creates git commits following Conventional Commits format with type/scope/subject. Use when user wants to commit changes, create commit, save work, or stage and commit. Enforces project-specific conventions from CLAUDE.md.
qa
Code review + QA vs Acceptance Criteria, including A+ status suggestions and review comment draft.