Skip to main content
skill CX Codex

session-flow — Claude Code skill: what it does, how to install

session-flow — a skill for Claude Code rebuilds the session’s goal, pivots, outcomes, current stage, and open decisions from its history. It starts after a session switch or context compaction.

MIT 118 installs ★ 40,997 updated 2026-10-24

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add Yeachan-Heo/oh-my-claudecode --skill session-flow -a claude-code
Open on GitHub

What session-flow does

The skill reconstructs how the current conversation progressed from user messages and tool results. It separates the original goal from explicit changes, records completed and abandoned paths, and marks decisions still waiting for the user. Each stage gets a compact evidence pointer such as an artifact path, URL, short quote, or tool result.

With no argument, it renders the full map and reconciles its own Tasks through TaskList, TaskGet, TaskCreate, and TaskUpdate when native Task tools are available. short returns only the goal, current stage, and Needs you; reset removes confirmed Tasks carrying the session-flow: managed stage marker. Model invocation is disabled, so the skill is run manually.

What it helps with

  • recover the goal after context compaction
  • separate completed work from planned stages
  • record pivots and abandoned directions
  • collect unresolved decisions in one map
  • sync reconstructed stages with session Tasks

Example prompts for the agent

  • Run session-flow and rebuild the current session map with evidence.
  • Run session-flow short and show the goal, current stage, and anything you need from me.
  • Run session-flow reset and remove only Tasks owned by this skill.

How to install session-flow

1Skills CLI (Vercel)

npx skills add Yeachan-Heo/oh-my-claudecode --skill session-flow -a claude-code

2Manually: put the files in place

~/.claude/skills/session-flow/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/session-flow/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about session-flow

How do I install session-flow in Claude Code?

Run npx skills add Yeachan-Heo/oh-my-claudecode --skill session-flow -a claude-code, then check ~/.claude/skills/session-flow/SKILL.md.

What does session-flow do?

It turns the conversation history into a compact map of the goal, stages, outcomes, pivots, dropped paths, and unresolved decisions. In its full mode, it also updates its own Tasks while preserving the [S<number>] and session-flow: managed stage markers.

What are the session-flow modes?

With no argument, the skill renders the full map and reconciles Tasks. short is read-only and shows the goal, current stage, and user decisions; reset discovers and deletes only confirmed Tasks owned by the skill.

Source text

SKILL.md · MIT
---
name: session-flow
description: Reorient in the current Claude Code session with an evidence-backed map of its goal, pivots, outcomes, current step, and open decisions.
argument-hint: "[short|reset]"
disable-model-invocation: true
---

# Session Flow

Build a compact, evidence-backed map of how this conversation actually unfolded so the user can reorient after switching sessions or compacting. This is an advisory summary, not a planner, executor, or replacement for the user's task list.

## Modes

- No argument: render the full map and reconcile its session-flow Tasks when native Task tools are available.
- `short`: return only the goal, current stage, and what (if anything) needs the user. Read-only; do not change Tasks.
- `reset`: discover and delete only Tasks owned by this skill, then confirm what was removed. Do not render a new map.

## Workflow

1. Reconstruct the flow from this conversation's user messages and tool results. Do not treat repository state alone as evidence that a stage happened. Separate the original goal from explicit goal changes, pivots, completed outcomes, dropped paths, and decisions still waiting on the user.
2. Make 4–8 meaningful stages when the history supports them; use fewer rather than padding sparse histories or inventing work. Use one outcome per stage:
   - `✅` completed with an outcome supported by the conversation
   - `▶` the current unfinished stage
   - `○` an explicitly planned but unstarted stage
   - `✂` dropped, with the stated reason
   - `↪` a pivot, with the old direction and the evidenced new direction
3. Give every stage one compact evidence pointer. Use a real URL or artifact path when one appears in the conversation; otherwise cite a distinctive short user quote or tool result. Never invent a link or state an inference as fact. Mark uncertain or pre-compaction reconstruction as `inferred`.
4. Keep the full map to at most 15 lines: one line per stage, plus concise goal, `Needs you`, and `Next` lines. Include open decisions in `Needs you`; say `none` when there are none. `Next` must be a concrete next action only when the conversation supports one.
5. In the default and `reset` modes, call `TaskList` and inspect every `[S<number>]` candidate with `TaskGet` before mutating it. A Task belongs to this skill only when its subject starts with `[S<number>]` and its description contains the exact marker line `session-flow: managed stage`. Never edit, complete, delete, or reuse an unmarked Task.
6. In the default mode, update owned Tasks that still represent a stage, create missing stages with `TaskCreate`, a subject beginning `[S<number>]`, and a description whose first line is the ownership marker followed by stage evidence. Match statuses to the map: completed (including dropped or pivoted) is `completed`, current is `in_progress`, and planned is `pending`. Delete owned Tasks for stages no longer in the reconstructed map with `TaskUpdate` status `deleted`; keep surviving stage numbers stable and avoid collisions with unowned Tasks.
7. The OMC continuation hook excludes Tasks with both the `[S<number>]` subject prefix and the exact ownership marker, so these descriptive records are not treated as unfinished work. Preserve both markers on every create or update. `short` must not call mutating Task tools.
8. For `reset`, discover owned Tasks with `TaskList` and `TaskGet`, then use `TaskUpdate` status `deleted` only on confirmed owned Tasks.
9. If the native Task tools are unavailable, render the map without claiming it was persisted. For `reset`, report that owned Tasks could not be inspected or removed; do not guess which Tasks belong to the skill.

## Output

Use a stable, concise shape:

```text
🎯 Goal: <goal and any evidenced change>
✅ S1 <stage> → <outcome> — evidence: <source pointer>
↪ S2 <old direction> → <new direction> — evidence: <source pointer>
▶ S3 <current stage> — evidence: <source pointer>
✂ S4 <dropped path> — <reason> — evidence: <source pointer>
⏸ Needs you: <decision or none>
➡ Next: <supported next action or none>
```

Omit example rows that do not apply. Keep the stage order stable across calls unless the conversation provides evidence to correct it; update the owned Tasks to match any correction.

© Yeachan-Heo · MIT · Yeachan-Heo/oh-my-claudecode

Similar skills

SKILL.md skills catalog →

From the same set48

The whole set →
diagram This skill picks a compact visual for code structure, from a call tree to a Mermaid diagram. Use it when prose makes relationships hard to follow. CX Codex +1 194installs ask-navigator ask-navigator — a skill that turns an unclear effort into a map of decision tickets on the repo's issue tracker. It works the frontier one ticket per session until the route clears, then hands decisions over without building anything. CX Codex +1 191installs loft loft resolves deadlocked design and logic questions by building disposable runnable prototypes that never merge into main. CX Codex +1 189installs intent Turns a pasted chat or problem report into a reviewed intent.md. It gives /launch a decision brief instead of code. CX Codex +1 187installs pr pr — a Claude Code skill that drafts pull request descriptions from the session paper trail. It compiles verified test evidence, visual summaries, and rollback risks into a markdown body. CX Codex +1 161installs map This Claude Code skill routes a task to the matching skill in the collection. It maps work to a delivery stage or a specific workflow, but does not carry out the task itself. CX Codex +1 160installs refit refit is a Claude Code skill that reviews OMC runtime traces to find agent workflow friction and propose targeted fixes to checks, configs, and instructions. CX Codex +1 158installs research The research skill investigates open questions in a codebase and its docs, then ties findings to sources. Use it when an unresolved fact affects your next step. CX Codex +1 1installs

Project sponsors

Companies that keep this analytics open