Borrowing it
Nothing to install: this file belongs to Koroqe/OPOS. 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/Koroqe/OPOS/main/.claude/skills/deliberate-decision/SKILL.mdgit clone --depth 1 https://github.com/Koroqe/OPOSWrote 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/koroqe/opos/deliberate-decision)<a href="https://agentmods.dev/skills/koroqe/opos/deliberate-decision"><img src="https://agentmods.dev/badge/skills/koroqe/opos/deliberate-decision/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/koroqe/opos/deliberate-decision"><img src="https://agentmods.dev/badge/skills/koroqe/opos/deliberate-decision.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 | $0.00070 | $0.04168 |
| Opus 5 | $0.00035 | $0.02084 |
| Sonnet 5 | $0.00014 | $0.00834 |
| Haiku 4.5 | $0.00007 | $0.00417 |
Grade A, and why
deliberate-decision 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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
deliberate-decision
When to use
When a high-level company decision needs systematic pressure-testing: strategic direction, hiring, market entry, major policy changes, cross-functional tradeoffs. NOT for routine tactical choices (use the chief-of-staff dispatcher or a single consult-agent instead — those are cheaper). The plan-critic pattern that's been load-bearing on 7 OPOS releases (v0.4.0 through v0.6.1) is now a first-class company process.
This is the framework's most expensive single skill — ~15 subagent invocations per default 2-round deliberation (per RISKS Risk 27). Use deliberately for decisions whose stakes justify the cost.
Inputs
proposal_text(orproposal_pathto a file containing the proposal). Required. Non-empty after trim; soft cap 15,000 chars (most 1-2-page strategic memos fit).proposer_agent— kebab-case agent name; required; must match an existingname:in.claude/agents/**/*.md.decision_arbiter— OPTIONAL; default = computed from escalation rule (see below).critics— OPTIONAL override; default = all dept-leads + escalation-target minus proposer.rounds— OPTIONAL; default2; allowed input range[1, 5].
Task-call pattern (direct, NOT through consult-agent middleware)
This skill spawns Task calls DIRECTLY — it does NOT invoke the consult-agent skill. Reasons:
consult-agentis a SKILL (a body of instructions), not an agent. You can'tTask → consult-agent; you'd execute consult-agent's body which itself uses Task. 6 sequential consult-agent invocations would block parallelism.- The simulation prompt template
consult-agentproduces is reproduced INLINE in this skill's Task calls (load critic agent definition + format the "You are SIMULATING<name>..." framing). - Audit-trail consequence: these Task calls do NOT generate
consult-agent/history/entries. The audit lives in (a).claude/skills/deliberate-decision/history/(one consolidated entry per deliberation), and (b) the decision artifact'sAuditsection (one line per Task-call summarizing each round). The framework'sconsult-agent/history/folder stays focused on user-invoked single-shot consultations.
What ships with it
2 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.
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 · 276 lines · 70 tokens per session scan A 7b77e16bcfca
deliberate-decision is a skill published in the GitHub repository Koroqe/OPOS (2 stars, last pushed 7d ago), licensed MIT. It adds 70 tokens to every session and 4,168 once invoked, about $0.0003 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
war-room
Convenes a multi-LLM expert panel to pressure-test hard-to-reverse decisions. Use when reversibility score is low and adversarial review is warranted.
forge
A structured discussion room for engineering and architecture decisions, bringing several named reasoning perspectives together. It gathers evidence and produces a combined verdict.
atelier
A structured creative discussion room that brings together several philosophical viewpoints. It focuses on writer’s block, content planning, creative habits, and managing the information you consume.
bazaar
Bazaar (集市) — Business & strategy deliberation room. Convene Schumpeter, Munger, Sun Tzu, Machiavelli, Taleb, and Kahneman for market decisions, pricing, investment, and competitive strategy.
clinic
A structured discussion room for psychological resilience, using viewpoints from psychologists and philosophers. It focuses on anxiety, procrastination, burnout, and recovering from loss.
hearth
A structured discussion room for relationship, family, parenting, and workplace conflict questions. It brings together several named philosophical and psychological viewpoints and combines them into a final assessment.