Install
$ agentstack add skill-skyf0xx-better-thinking-consensus-mapping ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Consensus Mapping
Measure the actual gradient of agreement across a group instead of forcing a binary vote that hides where the real disagreement lives.
Why
A binary vote collapses a spectrum of "strongly for" to "strongly against, will actively block" into a single number, hiding both near-unanimous soft support and a small but intense veto-level objection. Mapping the gradient makes the group's real state visible before it's acted on.
Use when / Don't use when
- Use when: a group decision needs real buy-in, not just a nominal majority; a quick vote feels like it's hiding real dissent.
- Don't use when: a simple majority vote is genuinely sufficient and buy-in from the minority isn't required for implementation to succeed.
Inputs → Outputs
- Inputs: a group facing a decision with varying levels of agreement.
- Outputs: a gradient map of the group's position, with any veto-level objections surfaced explicitly rather than averaged away.
Principles
- Use a gradient scale — enthusiastic support, support with reservations, neutral, disagree but will go along, block — rather than binary yes/no.
- A single strong "block" carries different weight than several "reservations" and should be surfaced, not averaged into the mean.
- The goal is often not unanimous enthusiasm but the absence of unaddressed blocking objections.
Procedure
- State the proposal precisely enough to be rated.
- Have each participant rate their position on a gradient scale, ideally simultaneously, to avoid anchoring on the first vocal response.
- Map the distribution: where does the group cluster, and where's the spread?
- Surface any block-level objections explicitly — don't let them wash out in an averaged score.
- For blocks or strong reservations, understand the underlying concern before proceeding.
- Decide: proceed with addressed concerns noted, revise the proposal, or escalate if a genuine block remains.
Common mistakes
- Converting the gradient back into a binary average, hiding exactly what the technique was meant to surface.
- Letting the loudest objector's position stand in for the whole group's gradient.
- Using this technique for decisions where genuine buy-in isn't actually necessary.
Examples
- A team deciding on a technical direction.
- A co-op's governance vote.
- A jury's deliberation check-in before a final verdict push.
Related
- [[interest-based-bargaining]] — the technique for resolving a surfaced block-level objection.
- [[retrospective-facilitation]] — uses this mapping when a retro's interpretation is contested.
- [[session-design]] — determines when this technique belongs in a session's agenda.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: skyf0xx
- Source: skyf0xx/better-thinking
- License: MIT
- Homepage: https://zenbin.org/p/better-thinking
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.