Borrowing it
Nothing to install: this file belongs to okuzpe/midas-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/okuzpe/midas-harness/main/.agents/skills/midas-tribunal/SKILL.mdgit clone --depth 1 https://github.com/okuzpe/midas-harnessWrote 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/okuzpe/midas-harness/midas-tribunal)<a href="https://agentmods.dev/skills/okuzpe/midas-harness/midas-tribunal"><img src="https://agentmods.dev/badge/skills/okuzpe/midas-harness/midas-tribunal/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/okuzpe/midas-harness/midas-tribunal"><img src="https://agentmods.dev/badge/skills/okuzpe/midas-harness/midas-tribunal.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 | $0.00078 | $0.01897 |
| Opus 5.5 | $0.00031 | $0.00759 |
| Sonnet 5.5 | $0.00016 | $0.00379 |
| Haiku 4.5 | $0.00008 | $0.00190 |
Grade A, and why
midas-tribunal 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 2mo 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
midas-tribunal — whole-project adversarial debate
Guard + state:
<paths.engine>/templates/skill-state-ritual.md(+AGENTS.md§ Safety / Path resolution). Readpaths.state. No artifacts on disk → report nothing to try and stop.
Does / Does not
| Does | Does not |
|---|---|
Argue whether decisions are right across {product}/*, rules, src/* |
Advance stage or set gate: passed |
Freeze ranked findings to {runs}/debates/debate-NN.md |
Grade its own arguments (producer ≠ judge) |
| Propose findings→action bridge on user go-ahead | Replace /close-sprint (that audits diff vs frozen rules) |
Standing tribunal at any stage. You convene and judge; debaters are build/scout tiers. Recommended checkpoints (from /midas-status, never forced): pre-go/no-go, pre-rules-freeze, pre-ship. Research rationale: <paths.engine>/research/debate-method.md. Record shape: <paths.engine>/templates/debate-record.md; shared audit fragments: <paths.engine>/templates/audit-checklists.md.
Lenses (parallel seats → synthesize)
Activate per scope; one persona + provocation + on-disk target each:
| Lens | Provocation | Target |
|---|---|---|
| Premortem | "12 months out, failed — why?" | whole |
| Skeptic | "Why build this?" | {product}/idea.md |
| Inverter | "What guarantees failure?" | {product}/roadmap.md |
| Economist | "Does the model close?" | {product}/business-plan.md |
| Competitor | "Why won't an incumbent crush this?" | {product}/market.md — when track: lite and the file is missing, skip this lens or use {product}/idea.md + {product}/business-plan.md; do not fail the skill |
| User | "Would a real user switch?" | idea + {product}/design-system.md |
| Design Critic | "Distinctive or generic slop? Logo-swap pass?" | {product}/design-direction.md + design-system + <paths.engine>/rules/visual-design.md § Product authenticity + UI src/* (+ {runs}/design/ if any) |
| ATAM | "Risks, sensitivity, tradeoffs?" | {product}/architecture.md + adr/* |
| Maintainer | "Will the next dev curse this?" | {product}/adr/* |
| Security (STRIDE) | "Where do I get in?" | <paths.engine>/rules/security.md + src/* |
| Reliability | "What fails silently till prod?" | architecture + <paths.engine>/rules/testing.md |
| Simplifier | "What survives the cut?" | roadmap + rules + scope |
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.
- 2mo ago First seen · 110 lines · 78 tokens per session scan A 05870356e2ba
midas-tribunal is a skill published in the GitHub repository okuzpe/midas-harness (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 78 tokens to every session and 1,897 once invoked, about $0.0003 per session on Opus 5.5. 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
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…