cogit
cogit: Cogito, ergo commit. Git for the intent behind agent-written code.
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Check it deeper on your machine
It has changed since its scan on 11 Nov 2026.
As a Claude Code plugin, install it and then ask Claude Code:
/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/erensrtky/cogit with scanskillsafety
Or from a terminal, clone it and run it:
git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/erensrtky/cogit'
It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.
Badge for your README
Markdown
[](/listings/erensrtky--cogit)HTML
<a href="/listings/erensrtky--cogit"><img src="/api/listings/erensrtky--cogit/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
You need Node 22.13+, Claude Code 2.1.275+ and a git repository.
npm install -g @cogit/cli
Then, in Claude Code:
/plugin install cogit --marketplace erensrtky/cogit
To get plugin updates on their own, turn on auto-update once: `/plugin` → Marketplaces → cogit → Enable auto-update. Claude Code leaves it off for marketplaces outside its own.
If the map stays empty, run `cogit doctor`.
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
.claude-plugin/marketplace.json · Manifest · 12 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.
- {
- "name": "cogit",
- "description": "cogit: Cogito, ergo commit. Git for the intent behind agent-written code.",
- "owner": { "name": "Eren Sertkaya" },
- "plugins": [
- {
- "name": "cogit",
- "source": { "source": "github", "repo": "erensrtky/cogit", "ref": "plugin" },
- "description": "Records what each session decided and why, and renders it as a static map."
- }
- ]
- }
README.md · README · 182 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.
- <p align="center"><img src="docs/images/cogit-mark.svg" width="96" alt="cogit"></p>
- # cogit
- **Git for the intent behind agent-written code.**
- <p align="center">
- <a href="https://www.npmjs.com/package/@cogit/cli"><img src="https://img.shields.io/npm/v/@cogit/cli?label=npm" alt="npm version"></a>
- <a href="https://github.com/erensrtky/cogit/stargazers"><img src="https://img.shields.io/github/stars/erensrtky/cogit" alt="GitHub stars"></a>
- <a href="LICENSE"><img src="https://img.shields.io/github/license/erensrtky/cogit" alt="MIT licence"></a>
- <a href="docs/guide/getting-started.md"><img src="https://img.shields.io/badge/works_with-Claude_Code-D97757" alt="Works with Claude Code"></a>
- <a href="docs/guide/codex.md"><img src="https://img.shields.io/badge/works_with-Codex_CLI-000000" alt="Works with Codex CLI"></a>
- </p>
- <p align="center"><img src="docs/images/cogit-descartes.jpg" width="360" alt="René Descartes with git branches running through his hair"><br><i>Cogito, ergo commit.</i></p>
- cogit records every message you send to an AI coding agent as a *thought commit*: what you
- asked, what came of it, and the message it answered. Your code commits point back to the
- thought behind them, so `cogit why` takes any line of code back to the reason it exists.
- Agent memory helps your agent remember. cogit helps you understand.
- It runs as a plugin in your coding agent and works through its hooks, so the record is written
- while you work, not reconstructed from the diff afterwards.
- **[Click through a saved map](https://erensrtky.github.io/cogit/demo/)**: no install, no server.
- It's the page `cogit open` writes, built from sample data and read-only.
- ## Why
- I started by copying code out of ChatGPT, then moved to browser tools, editor extensions and now
- terminal agents. Each step moved the code further from me, and I kept feeling something was
- slipping away. When you write code yourself, it sinks in bit by bit: you know why that table
- exists and why you wrote that class. When an agent writes it, that feeling goes away.
- The information isn't really gone. It sits in your messages, the agent's replies and your commits,
- just in separate places. cogit ties them together, so you can always walk back and see why
- something was done. It helps most when you juggle projects: I run 5-10 agents at once across 2-3
- of them, and a few minutes later I can lose track of what I did where.
- <img src="docs/images/why-abstraction.png" alt="A conceptual chart from machine code to software factories: abstraction keeps rising, while how much of the why you can still trace falls sharply once AI starts writing code. cogit keeps what falls away.">
- It's bigger than one person's memory: a reviewer sees what changed, not why.
- [More, with research and sources](docs/guide/why.md).
- cogit isn't:
- - **Agent memory** (OpenViking, Mem0): that helps your agent recall what you talked about.
- - **A token saver** (RTK, Headroom): that sends the model less.
- - **A code map** (graphify): that shows how a codebase fits together.
- - **An orchestrator** (Herdr, Conductor): that runs many agents at once.
- - **A planning framework** (BMAD, Spec Kit): that decides what to build next.
- - **An AI review bot** (CodeRabbit, Greptile): that comments on whether a diff looks right.
- It answers the one question they leave open: why is this code the way it is? I use several of
- them alongside it.
- ## See it
- <img src="docs/images/map.png" alt="The map: sessions as a git graph, each with its messages, branches, commit chips and a left off here marker">
- *Your sessions as a git graph — one row per message, the decision behind it, and where you left
- off.*
- <img src="docs/images/shape.png" alt="A message opened on its Shape tab: a flowchart of what the change does, under the tabs Intent, Shape and Code">
- *A message that landed commits opens as Intent, Shape and Code: why it happened, a picture of
- what the change does, and the diff.*
- <img src="docs/images/tasks.png" alt="The Tasks panel: suggested items with Accept and Dismiss, open items with Done, and a Done section">
- *Tasks — work that came up in a session and didn't get finished, caught when the session closes.
- You accept, dismiss or close each one.*
- <img src="docs/images/files.png" alt="The Files view: a changed file opened, listing the messages that touched it with each message's reason and the option it rejected">
- *A changed file opens its history: every message that touched it, and the reason behind each —
- including the option that was rejected.*
- ## What it does
- - **Every message becomes a thought commit**: the question, the outcome, the decisions with
- their reasons and the options that were rejected, and which earlier message it continues.
- - **A map of your sessions**: a git graph of your conversations with branches, decisions, a
- "Your turn" inbox, and Resume and Fork buttons that copy the command to reopen a chat or
- continue it as a new one.
- - **Commits point back to their reason**: a `Thought:` trailer on each commit;
- `cogit show <sha>`, `cogit blame` and `cogit why` follow it back.
- - **Intent, Shape, Code**: a message that landed commits shows why it happened, a small
- picture of what the change does (a diagram, a before/after or interface table, an example
- or plain steps), and the diff, in one place.
- - **Tasks**: when a session ends, a small model catches the work that came up and didn't get
- finished as a few user-level items; you accept, dismiss or close them (`cogit captures`, and
- on the map). Off by default: `cogit config set captures true`.
- - **Pull request descriptions with the decisions**: `cogit pr` writes the goal, the
- decisions and the rejected options, never the raw chat. `cogit pr --install-action` adds a
- GitHub Action that posts them on every pull request.
- - **Teams share the record through git**: after a pull, your teammates' sessions are on the
- map too, with who ran them and what changed most.
- - **The agent's own reasons, or the cheapest record**: a small model records in the
- background and never interrupts the agent. By default, when a session ends, the model it ran
- on reopens the whole conversation and corrects the record with what only it saw, for about
- one more message. Economical leaves it all to the small model: under 2 cents per 20 messages
- in our measurement.
- - **No server, no account**: it runs on your machine. Nothing leaves it unless you say so: `cogit
- init` asks whether to share the record (titles, decisions and reasons) with your team. If you
- do, `git push` sends it to your own repository, outside your branches, so it never shows up in
- a pull request or `git status`. Your chats stay local, `cogit prune` deletes old sessions, and
- key and token patterns are redacted.
- - **The agent gets the context too**: a new session starts where the last one left off, and
- the agent can look up what was decided and rejected with `cogit why`. It works alongside
- memory tools; it doesn't replace them.
- ## Install
- You need Node 22.13+, a git repository, and Claude Code 2.1.275+ or Codex CLI 0.167+.
- ```bash
- npm install -g @cogit/cli
- ```
- Then, in Claude Code:
- ```text
- /plugin install cogit --marketplace erensrtky/cogit
- ```
- To get plugin updates on their own, turn on auto-update once: `/plugin` → Marketplaces →
- cogit → Enable auto-update. Claude Code leaves it off for marketplaces outside its own.
- In Codex, from a terminal:
- ```bash
- codex plugin marketplace add erensrtky/cogit --sparse .agents
- codex plugin add cogit@cogit
- ```
- Then start Codex in a project and accept the hooks review it shows; Codex asks again after
- every cogit update. Details in [Codex](docs/guide/codex.md).
- If the map stays empty, run `cogit doctor`.
- ## Quick start
- ```bash
- cd your-project
- cogit init # a few questions: git, transcript retention, team setup, language
- ```
- Work with Claude Code or Codex as usual; recording needs nothing from you. Then open the map:
- ```bash
- cogit open .
- ```
- ## Guide
- - [Getting started](docs/guide/getting-started.md): what `init` asks, your first session,
- setting up a team
- - [The map](docs/guide/map.md): sessions, branches, the inbox, files, search,
- resuming and forking a session
- - [Reading the lineage](docs/guide/reading-the-lineage.md): `log`, `show`, `blame`, `why`,
- `search`
- - [Pull requests](docs/guide/pull-requests.md): `cogit pr`
- - [Teams and git](docs/guide/teams-and-git.md): what is shared, the trailer, the hooks
- - [Recording and cost](docs/guide/recording-and-cost.md): who writes the record, what it
- costs
- - [Loops, sandboxes and agent factories](docs/guide/loops-and-sandboxes.md): recording
- `claude -p` loops and sandboxed runs
- - [Codex](docs/guide/codex.md): installing in Codex, the hooks review after each update,
- `codex exec`, limits
- - [Privacy](docs/guide/privacy.md): what is recorded and what never leaves your machine
- - [Settings](docs/guide/settings.md): every setting, explained
- - [Troubleshooting](docs/guide/troubleshooting.md)
- - [FAQ](docs/guide/faq.md): questions people asked after the launch
- - [Why cogit](docs/guide/why.md): AI made code faster and review slower
- The record format is in [docs/format.md](docs/format.md).
- ## Licence
- MIT — see [LICENSE](LICENSE).
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.