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 OKHP3/skillz --skill okhp3-equilibrium-reviewgit clone --depth 1 https://github.com/OKHP3/skillzWrote 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/okhp3/skillz/okhp3-equilibrium-review)<a href="https://agentmods.dev/skills/okhp3/skillz/okhp3-equilibrium-review"><img src="https://agentmods.dev/badge/skills/okhp3/skillz/okhp3-equilibrium-review/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/okhp3/skillz/okhp3-equilibrium-review"><img src="https://agentmods.dev/badge/skills/okhp3/skillz/okhp3-equilibrium-review.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 | $0.00100 | $0.02341 |
| Opus 5 | $0.00050 | $0.01171 |
| Sonnet 5 | $0.00020 | $0.00468 |
| Haiku 4.5 | $0.00010 | $0.00234 |
Grade A, and why
okhp3-equilibrium-review 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 12d 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
okhp3-equilibrium-review
OverKill Hill P³ · overkillhill.com · github.com/OKHP3
The Equilibrium Review skill turns agreement and disagreement into a traceable decision. It evaluates an artifact without assuming that a polished answer, majority vote, or self-review is proof of correctness.
Purpose
Use this skill as a quality gate around an artifact-producing workflow. The artifact may be a paper, research memo, spreadsheet, dashboard, Outlook assessment, hypothesis, decision recommendation, or Agent Skill. The skill's default job is to review and improve the decision record, not silently rewrite the artifact or take consequential action.
The equilibrium metaphor is operational, not a claim that language-model reviewers compute a formal Nash equilibrium. A useful review has provisional harmony when independent reviewers converge for evidence-backed reasons. It has productive disharmony when they identify a material difference. A disruptor is introduced to search for falsifiable counterexamples when harmony may be false. A negotiator resolves disagreement from evidence, not from vote counting.
Scope
| In scope | Out of scope |
|---|---|
| Claim, evidence, utility, safety, portability, and reader-usefulness review | Inventing evidence or declaring perfection |
| Conditional five-role multi-agent review | Unbounded agent debate or ceremonial dissent |
| Hypothesis and measurement-design audit | Performing a statistical test without appropriate data or expertise |
| Review records, ledgers, decision gates, and revision plans | Autonomous publication, sending messages, or changing source systems |
| Domain adapters for documents, data, reports, and skills | Replacing legal, medical, financial, security, or other specialist authority |
Operating contract
Required inputs
Collect these before review:
- A frozen artifact or a clearly identified artifact version.
- One decision question, such as “Is this thesis ready for publication within its stated scope?”
- Acceptance criteria that distinguish correctness, usefulness, safety, and evidence sufficiency.
- A claim and evidence ledger, even if the initial version is small.
- Known constraints, risks, dependencies, and intended audience.
- A development set and, when release claims matter, a protected or external holdout. Do not call a holdout protected if the optimizer has seen it.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/equilibrium-review-record.json 828 B
- benchmarks/benchmark.json 921 B
- benchmarks/evolution-review-2026-07-28.json 2.6 KB
- evals/evals.json 1.9 KB
- README.md 2.8 KB
- references/domain-adapters.md 1.9 KB
- references/review-protocol.md 2.3 KB
- references/role-prompts.md 2.5 KB
- scripts/run_equilibrium_review.py 19 KB runs code
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.
- 12d ago First seen · 245 lines · 100 tokens per session scan A 24aad5cce75c
okhp3-equilibrium-review is a skill published in the GitHub repository OKHP3/skillz (3 stars, last pushed today), licensed MIT. It adds 100 tokens to every session and 2,341 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.
Other skills, from other repositories
ontoly-software-graph
Use Ontoly's deterministic Software Graph and MCP capabilities for architecture review, request tracing, dependency analysis, configuration lookup, and impact analysis before falling back to source-file search.
kelly-pr-review
GitHub pull request review desk (Busabase App-in-Skill) using the gh CLI for real GitHub access, an AirApp review UI for human approval, and a trusted gh pr review execution step. Use when the user invokes /kelly-pr-review or $kelly-pr-review, asks to review GitHub PRs, generate a PR review batch…
drupal-security-review
Use when auditing Drupal 11 custom modules/themes for security issues such as unsafe input handling, XSS risks, SQL injection, and access control gaps.
find-verified-code-review-agent
Find a Verified Code Review Agent. Agent discovery, trust verification, and capability routing powered by Aidress — the coordination registry for autonomous AI agents. Use for software agent discovery, trust verification, and capability routing — via Aidress (https://api.aidress.ai).
baoyu-comic
A tool for creating original educational comics that explain knowledge or ideas through multiple illustrated panels. It supports different art styles and tones and can create several comics in one batch.
refactor-advisor
A code review helper that finds common design and maintenance problems in a codebase and suggests ways to restructure the code.