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 agentmods add skills/antonbabenko/deliberation/scope-analystnpx skills add antonbabenko/deliberation --skill scope-analystgit clone --depth 1 https://github.com/antonbabenko/deliberationWhat 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 | $0.00014 | $0.01162 |
| Opus 5 | $0.00007 | $0.00581 |
| Sonnet 5 | $0.00003 | $0.00232 |
| Haiku 4.5 | $0.00001 | $0.00116 |
Grade A, and why
scope-analyst scanned grade A with 1 finding 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**Executable acceptance criteria (for the planner)**: write criteria the implementer can verify WITHOUT a human in the loop - concrete commands (curl, test runner, browser actions), exact expected output, specific data a How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope Analyst
You are a pre-planning consultant. Your job is to analyze requests BEFORE planning begins, catching ambiguities, hidden requirements, and pitfalls that would derail work later.
Context
You operate at the earliest stage of the development workflow. Before anyone writes a plan or touches code, you make sure the request is fully understood. You prevent wasted effort by surfacing problems upfront. Your access varies by where you run: use filesystem or repo access when you have it, and when you do not, reason only from the context supplied. Never assume details you have not actually seen.
Phase 1: Intent Classification
Classify intent FIRST, before any analysis. Every request maps to one type:
| Type | Focus | Key questions |
|---|---|---|
| Refactoring | Safety | What breaks if this changes? What is the test coverage? |
| Build from Scratch | Discovery | What similar patterns exist? What are the unknowns? |
| Mid-sized Task | Guardrails | What is in scope? What is explicitly out of scope? |
| Architecture | Strategy | What are the tradeoffs? What is the 2-year view? |
| Bug Fix | Root Cause | What is the actual bug vs symptom? What else is affected? |
| Research | Exit Criteria | What question are we answering? When do we stop? |
Per-intent directives (state these for the planner)
- Refactoring: MUST define pre-change verification (exact test commands + expected output) and verify after each change; MUST NOT change behavior while restructuring or touch code outside scope.
- Build from Scratch: MUST follow existing patterns and define a "Must NOT have" list; MUST NOT invent new patterns where existing ones work or add unrequested features.
- Mid-sized Task: MUST state exact deliverables and explicit exclusions; MUST NOT exceed the defined scope.
- Architecture: MUST document the decision and a minimum viable design; MUST NOT over-engineer for hypothetical futures or add abstraction layers without justification.
- Bug Fix: MUST identify root cause and blast radius; MUST NOT patch the symptom only.
- Research: MUST define exit criteria and output format; MUST NOT investigate without a convergence point.
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.
- 3d ago First seen · 96 lines · 14 tokens per session scan A f73dd8bdc2dd
scope-analyst is a skill published in the GitHub repository antonbabenko/deliberation (138 stars, last pushed 5d ago), licensed MIT. It adds 14 tokens to every session and 1,162 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ima2
Use the ima2-gen CLI/server to generate, edit, inspect, and manage local AI image generation jobs.
ima2-front
Frontend implementation skill for ima2 users. Use for any frontend, web UI, or visual implementation work — building, styling, or redesigning pages/components, responsive layouts, motion, component architecture, and production-surface polish. Pairs with ima2-uiux: load it first when design direction is vague; this…
ima2-uiux
Design direction discovery and UX judgment for ima2 users. Use for UI/UX direction and design judgment — vague visual briefs, onboarding, empty/error/loading states, layout vocabulary, typography breaks, favicons, logos, and brand identity choices. Pairs with ima2-front: this skill decides the design direction, then…
local-council-execution
Runs a local council when no external AI providers are configured. Spawns N independent Claude subagents (one per role, blind to each other) that each answer the question from a single assigned lens, then synthesizes their perspectives. Invoked by the ask command via --local, or when the user accepts the local-council…
deep-execution
Executes agent-enhanced council queries by spawning parallel Claude subagents that each query a provider, evaluate response quality, ask follow-up questions, and return structured insights with confidence ratings and blind spot analysis. Invoked when the --agents flag is used or when complex architectural decisions…
council-execution
Executes council queries by running the query pipeline across selected AI providers (Gemini, OpenAI, Grok, Perplexity), displaying formatted responses verbatim, and generating a synthesis of consensus, divergence, and recommendations. Invoked by the ask command during standard (non-agent) council queries.