flow

An autonomous method for working through one difficult goal by trying assumptions, following their consequences, recording dead ends, and changing direction when needed.

In plain words
What is it for?
It can be used for difficult mathematics, theory, design, debugging, or strategy problems with one specific target.
Why use it?
It helps with problems where a direct attempt repeatedly gets stuck and the cause of failure is not obvious.

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/quantumbfs/sci-brain/flow
Any agent
npx skills add QuantumBFS/sci-brain --skill flow
Clone the repo
git clone --depth 1 https://github.com/QuantumBFS/sci-brain

Made for: Claude Code, Codex.

Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,793 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 $0.00087 $0.02793
Opus 5 $0.00044 $0.01396
Sonnet 5 $0.00017 $0.00559
Haiku 4.5 $0.00009 $0.00279

Measured 2d ago against content hash a8a3cda63453, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

flow 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/flow/SKILL.md · 204 lines

How it starts

The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Flow

A deep-thinker that conquers one hard problem by autonomous search, modeled on a CDCL/DPLL SAT solver. Given a goal, it iterates — assume, follow consequences, hit walls, learn from the walls, jump back, and re-aim when truly stuck — until a solution emerges or it converges on an equally-valuable reachable goal.

Scope. Goal-locked, fully autonomous, domain-agnostic. This is not brainstorm-ideas (open-ended, collaborative, research-only). Use flow when you already have a specific hard target and want a relentless solver thrown at it. KB-optional: if <project>/.knowledge/INDEX.md exists, treat its papers as a fact source for propagation; never require it.

The mental model

Solver concept Here
Variable assignment (Decide) what-if: assume a new condition
Unit propagation (BCP) simulate: run consequences forward, reflect
Conflict a contradiction or dead-end on the current branch
Conflict analysis + learned clause the note taken after every trial
Non-chronological backtracking backjump to the real cause, not one step
Restart (clauses kept) pivot: re-aim the goal; notes survive
Decision heuristic (VSIDS) pick the lever that shrinks distance most + is easiest; favor conditions seen in recent conflicts

State to track

Maintain these throughout (in the journal file, see below):

  • GOAL — restated crisply, with a concrete success test: how will I know it is solved?
  • TRAIL — ordered list of decisions + propagated facts, each tagged with a decision level.
  • GOAL_STACK — subgoals spawned by what-if recursion (current goal on top).
  • NOTES — learned clauses: trigger conditions → outcome → reusable lesson. These are the whole point — they prune future search and guide backjumps.
  • distance — a rough estimate of how far the current state is from GOAL.
  • no_progress — consecutive trials with no distance drop (drives PIVOT).

Read the full file on GitHub · 204 lines

Files

What ships with it

1 file 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.

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 · 204 lines · 87 tokens per session scan A a8a3cda63453

Subscribe to this mod's changes

flow is a skill published in the GitHub repository QuantumBFS/sci-brain (81 stars, last pushed 5d ago), licensed MIT. It adds 87 tokens to every session and 2,793 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens