predict

A structured discussion before implementing a significant gflow-cli change, in which five expert viewpoints examine the proposal and agree on a GO, CAUTION, or STOP result.

In plain words
What is it for?
Use it before changing transports, authentication, selectors, data schemas, command-line behavior, or backlog items that have an investigation gate.
Why use it?
It surfaces architecture, security, performance, and user-facing problems before code is written, when changes are cheaper to revise. It also identifies proposals that need more investigation.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/ffroliva/gflow-cli/predict
Any agent
npx skills add ffroliva/gflow-cli --skill predict
Clone the repo
git clone --depth 1 https://github.com/ffroliva/gflow-cli

Made for: Claude Code, Codex.

Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,367 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00078 $0.02367
Opus 5 $0.00039 $0.01184
Sonnet 5 $0.00016 $0.00473
Haiku 4.5 $0.00008 $0.00237

Measured 2d ago against content hash ad22c804e7db, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

predict 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 2d 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.

skills/predict/SKILL.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

predict — Pre-Implementation Multi-Persona Analysis

Structured pre-implementation review. Five expert personas assess the proposal independently, then debate, then converge on a verdict with a confidence score. Surfacing architectural, security, performance, and UX flaws before the first commit is the cheapest place to catch them.


When to invoke

Use before implementing any of:

  • A new transport strategy (sapisidhash, cdp_attach, official_veo)
  • Auth flow changes (new strategy, G12 bypass technique, cookie extraction)
  • Selector cascade redesigns affecting ONBOARDING_SELECTORS, NEW_PROJECT_SELECTORS, FRAME_SLOTS_STRUCT
  • Schema migrations in gflow_cli/data/
  • New CLI surface or exit-code changes
  • Any backlog item with an "investigation gate" in PLAN.md before coding

Skip for: trivial bug fixes (< 10 lines, isolated, no boundary cross), already-approved PLAN.md tasks entering EXECUTE, pure doc changes.


Invocation

/gflow:predict <proposal>

<proposal> is a short description of what you intend to build or change — one paragraph is enough. Examples:

  • "Wire SAPISIDHASH auth header into _post_json for all aisandbox-pa routes (Issue #15)"
  • "Add CDP-attach transport as opt-in --transport cdp_attach alongside ui_automation"
  • "Redesign gflow video batch to use a local manifest ledger for skip-already-done"
  • "Add AuthBrowserBlockedError to internal_chromium.py when Google rejects bundled Chromium"

Protocol

Phase 1 — Persona briefings (parallel)

Dispatch five personas simultaneously. Each reads AGENTS.md, PLAN.md, KNOWN_ISSUES.md, and the relevant source files for the proposal. Each assesses independently — no persona sees another's output during Phase 1.

Persona 1 — Architect

Scope: hexagonal target, modular-monolith current shape, dependency direction, module boundary rules.

Asks:

  • Does this proposal respect the dependency rule (interfaces → application → domain ← infrastructure)?
  • Which module does this live in? Does it fit cleanly or does it need a new module, and if so, is that justified?
  • Will this make the eventual DDD graduation harder or easier?
  • Are there hidden coupling risks (e.g., a transport leaking into cli.py, a domain model importing from infrastructure)?
  • Does the proposed shape match the existing pattern (Protocol-based ports, frozen dataclasses for value objects, structlog for all logging)?

Read the full file on GitHub · 210 lines

Changes

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.

  1. 2d ago First seen · 210 lines · 78 tokens per session scan A ad22c804e7db

Subscribe to this mod's changes

predict is a skill published in the GitHub repository ffroliva/gflow-cli (136 stars, last pushed 2d ago), licensed MIT. It adds 78 tokens to every session and 2,367 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

github-issue-triage

Issue triage and lifecycle management agent for ZeroClaw. Use this skill whenever the user wants to: triage open issues, close stale/duplicate/fixed issues, apply labels, run a backlog sweep, enforce the current issue stale policy, or handle a specific issue. Trigger on: 'triage issues', 'issue triage', 'sweep…

zeroclaw-labs/zeroclaw · 140 tokens

docs-planner

Identify documentation gaps and prioritize the docs backlog. Use when planning a docs improvement sprint, after signals surface repeated friction, when new SDK features ship without docs, or for periodic health assessment. Also triggers on "plan docs work", "what docs need writing", "prioritize the backlog", "docs…

strands-agents/harness-sdk · 73 tokens

team-workflow

Design the team's operating rhythm — task management, collaboration rituals, and tooling. Use when the day-to-day cadence needs structure. For a time-boxed sprint, use design-sprint-plan.

Owl-Listener/designer-skills · 43 tokens

design-sprint-plan

Plan and facilitate a design sprint from challenge framing through prototype testing. Use when compressing discovery into days. For ongoing team cadence, use team-workflow.

Owl-Listener/designer-skills · 37 tokens

Technical Debt Tracking with PMAT

Tracks and manages technical debt using PMAT (Pragmatic AI Labs MCP Agent Toolkit). Use this skill when: User asks about technical debt, TODO comments, or code quality issues Planning sprint work and need to prioritize debt repayment Conducting code audits or technical debt assessments Tracking debt accumulation…

paiml/paiml-mcp-agent-toolkit · 123 tokens

backlog

Capture single backlog items, or list and triage an existing project backlog. Use this skill whenever the user wants to file a bug, feature request, or backlog item without writing a full PRD, including casual requests mid-conversation like "create an issue for that", "add this to the backlog", or "file a quick bug…

sammcj/agentic-coding · 182 tokens