Menu
View on GitHubGitHub

When agents write the code, trust is in short supply.

05 is the acceptance layer for AI-written code. The agent declares what it will do before it starts; 05 seals that plan, checks the result on the change and signs the evidence. When the agent is done, you receive the intent and outcome results. No pull request to review. If something did not match, you read a brief that outlines the critical details, instead of the diff. When several agents work in one repository, 05 keeps them out of each other's way.

Install

Install scriptcurl -fsSL https://use05.dev/install.sh | sh
npm, this machinenpm install -g @use05/cli
npm, one projectnpm install --save-dev @use05/cli

Then, in your repository, run use05 init (npx use05 init for a project install). macOS and Linux. Read the docs.

Read the docs View on GitHub

Open source. The command line tool and the runner are free under Apache-2.0 at github.com/use05-dev/use05.

Terminal output. use05 prove runs ./test.sh on staged files and reports Proved with the tree hash, 10 ms duration, a receipt reference and the signing key, plus a note that a receipt made on this machine is advisory. use05 verify then reports Valid: the signature checks out and the tree matches the index.

Stop reading every line. Accept changes on evidence.

An agent can write a change in minutes, and nobody can read every line at that pace. What keeps up is saying what you want before the work starts, then accepting the change when the evidence shows it was done.

Without 05

  • You read every line the agent wrote.
  • You take "tests pass" on the agent's word.
  • You ask the agent to follow the rules and hope it does.
  • Review becomes the bottleneck.

With 05

  • The agent states its plan before it starts.
  • Your checks run on the change, and the result is signed.
  • 05 compares what changed with what was planned.
  • You approve from one brief, then land and push. No pull request needed.

Every change comes with signed evidence, not "trust me, tests pass."

Agents write code faster than people can review it

Review is the bottleneck

Agents produce changes faster than anyone can read them, so reading every line stops working.

"Tests pass" is only a claim

When an agent says its tests pass, you have its word. It becomes a fact when something independent runs the checks on the change.

Prompting is not a control

Telling an agent the rules does not stop it from breaking them. A real control blocks the change when a rule is broken.

You own the request and the acceptance. Agents own the plan and the work. 05 holds them to the plan.

One change from start to finish. The step-by-step page explains each stage.

How a change moves through 05 Seven steps left to right. A person asks and the agent declares its plan, which 05 seals. Agents work, watched by advisory hooks. The runner runs the checks on the change and signs a receipt. A drift check compares the plan with what changed. A one-page brief is produced. A human approves with a passphrase-signed approval. The change lands as a commit and is pushed; a CI required check enforces it, and the pre-push gate is advisory. A dashed side path shows a logged break-glass bypass from the brief to the landing. Humans own the request and the acceptance; agents own the plan and the work. HUMANS OWNTHE REQUEST AGENTS OWN THE PLAN AND THE WORK05 HOLDS THEM TO THE PLAN HUMANS OWNTHE ACCEPTANCE HUMAN 1 Human asks,agent plans The plan issealed beforethe first edit. AGENT 2 Agentswork Claude Code,Codex, others.Hooks watch(advisory). 05 RUNNER 3 Runner provesand signs Runs checks onthe change andsigns a receipt. 05 CHECK 4 Driftcheck Compares theplan with whatchanged. No AIdecides. 05 BRIEF 5 One-pagebrief Intent, outcome,evidence, drift,unknowns, howto undo. HUMAN 6 Humanapproves Signed with apassphrase-protected key. GIT HOST 7 Landand push CI requiredcheck enforces.Pre-push gateis advisory. Break-glass bypass (logged) Human step Agent step 05: local CLI and portable runner Git host: a thin, replaceable enforcement adapter How a change moves through 05 Seven steps top to bottom. A person asks and the agent declares its plan, which 05 seals. Agents work, watched by advisory hooks. The runner runs the checks on the change and signs a receipt. A drift check compares the plan with what changed. A one-page brief is produced. A human approves with a passphrase-signed approval. The Git host enforces the merge. A dashed side path shows a logged break-glass bypass from the brief to the landing. Humans own the request and the acceptance; agents own the plan and the work. HUMANS OWN THE REQUEST AGENTS OWN THE PLAN AND THE WORK HUMANS OWN THE ACCEPTANCE 1 HUMAN Human asks, agent plans The agent declares its plan; 05seals it before the first edit. 2 AGENT Agents work Claude Code, Codex, or any other agent.Hooks watch the session (advisory). 3 05 RUNNER Runner proves and signs Runs the checks on the changeand signs the result as a receipt. 4 05 CHECK Drift check Compares the plan with what changed.Fixed rules decide, never an AI. 5 05 BRIEF One-page brief Intent, outcome, evidence, drift,unknowns, and how to undo it. 6 HUMAN Human approves Approval signed with apassphrase-protected key. 7 GIT HOST Land and push A CI required check enforces it;the pre-push gate is advisory. Break-glass bypass (logged) Human step Agent step 05: local CLI and portable runner Git host: replaceable enforcement adapter

What you get with 05

Free, local

A command line tool that stays on your machine

The use05 command line tool is free and open source. It runs on your machine, with no account and no telemetry. Nothing is uploaded.

Privacy
Evidence

Signed receipts anyone can verify

The runner runs your checks on the change and signs the result. Anyone can verify the receipt offline, without an account.

How receipts work
Intent

The plan comes first

The agent declares its plan and the files it will touch before it starts, or you set them with use05 start --scope. 05 then compares what changed with that plan. If no scope was declared, 05 says it could not check. No AI decides whether a change passes.

See the steps
Review

A brief instead of the diff

When the agent is done, you get one brief with the intent, the outcome and the critical details. It takes minutes to read. When everything matched, it says there is nothing to read.

What the brief contains
Policy

Rules that only get tighter

Your rules live in a policy file in the repository. An organisation can sign a minimum that teams can tighten but never loosen. Folders and files can be locked, append-only, protected from deletion or closed to reading. Approvals are signed with a passphrase-protected key, and every bypass is logged.

Locked folders and file rules
Gates

Hooks, a pre-push gate and CI

Hooks for Claude Code and Codex, a git pre-push gate and a CI template. Each one is true about what it can and cannot enforce.

05 with Claude Code and Codex

What the command line tool actually prints

These are screenshots of the real use05 tool on a demo repository, not mockups. Notice how often it says advisory: 05 tells you how strong its own controls are.

  1. Terminal output. use05 prove runs ./test.sh on staged files and reports Proved with the tree hash, 10 ms duration, a receipt reference and the signing key, plus a note that a receipt made on this machine is advisory. use05 verify then reports Valid: the signature checks out and the tree matches the index.
    Prove, then verify. use05 prove runs a check on the change and signs a receipt. use05 verify checks the receipt offline, with no account and no network.
  2. Terminal output. use05 prove records that ./fail.sh failed with exit 1 and says the receipt says so, showing the last line of output. use05 verify then reports a valid receipt whose recorded check did not pass, and the command exits with code 2.
    Failures are evidence too. A failing check is still recorded in a valid receipt, and use05 verify says clearly that it did not pass.
  3. Terminal output. use05 init reports seven changes: a policy file proposing the test check, a .gitignore for agents' unsealed declarations, a signing key for this machine, Claude Code hooks with permission for the agent to run start, prove, finish, brief and land, Codex hooks, a git pre-push hook, and a block added to AGENTS.md. It then lists what is not covered: no approver key yet and no merge enforcement.
    Set up in one command. use05 init lists what it changed, what it left alone and what is not covered yet. use05 uninstall reverses it.
  4. Terminal output of the bare use05 command. The task is Stop retrying failed charges forever, started at this machine (unverified), with the intent card written but not approved; three files are staged and approval is required. Agent hooks are on, the pre-push hook is on and advisory, the CI gate is off. A numbered menu follows.
    Bare use05 shows where you stand. It shows the current task, whether the staged change would be allowed and which controls are on, followed by a short menu.
  5. Terminal output of use05 brief. Intent: cap retries at three, scope src/billing, risk high because of a migration and money code. Outcome: three files changed, two outside scope, including a migration and package.json. Evidence: the test check has not been run. Drift: a protected path changed, scope exceeded, dependency files changed, and the claim All tests pass is unsupported. Decision: approval required, two things hold the change back.
    The brief replaces the diff. It covers the intent, the outcome, the evidence, anything that drifted from the plan, the approvals, what is unknown and how to undo it, then gives one decision with its reasons.
  6. Terminal output of use05 brief on an agent's branch. The task Add the support address to receipts has scope src/receipts and low risk. One file changed, the test check passed, nothing differs from the intent, and the verdict is ALLOW, nothing to read.
    When everything matched, there is nothing to read. The change stayed inside its declared scope and its checks passed, so the brief says so in one line.
  7. Terminal output of use05 land. It lands claude/receipt-footer on main as a fast-forward, removes the agent's worktree and deletes the branch, then suggests pushing main.
    Land it and nothing is left behind. use05 land moves an allowed change into its target branch, then removes the agent's finished branch and worktree.
  8. Terminal output of git push. 05 first proves the missing test check for the pushed commit, then stops the push: approval required, because a protected file changed. Break glass is logged. It states that git push --no-verify skips the hook and that branch protection can stop that.
    A push the gate does not allow. The pre-push hook stops it, names the rule and the next step, and says that --no-verify would skip it, because the hook is advisory.
  9. Terminal output. use05 prove passes the test check. use05 approve shows what is being approved, three files, risk high, three findings, and that the approval is bound to this exact content and expires in seven days. The brief now ends with ALLOW, read the notes: two files outside the declared scope and a dependency change.
    A person approves, with a passphrase an agent does not have. The approval is signed, tied to this exact content and expires. The brief then says allow.
  10. Terminal output. A Claude Code PreToolUse hook payload that edits .05/policy.toml is answered with a deny decision: the file is protected and a person must approve the intent first.
    An agent that edits the rules is stopped. Hooks refuse risky commands and protected paths, and tell the agent to ask a person. They are advisory, and step aside if 05 itself breaks.
  11. Terminal output of use05 doctor. Setup, keys, controls and record sections with check marks. Agent hooks and the pre-push hook are on and described as advisory, the approver key is passphrase protected, and the CI gate is missing with a note that without it nothing is stronger than advisory.
    Doctor tells you how strong each control is. Hooks and the pre-push gate are advisory. Without a CI check, nothing is stronger than advisory, and doctor says so.
  • ≈ 8 ms added to each agent action by 05's hooks, measured on a repository of 3,000 files.

Measured on the current release in a dev container. Your machine will differ. More measurements are on the receipts page.

A control is only as strong as where it runs. 05 tells you which is which.

Hooks, the pre-push gate and receipts made on your machine are advisory, because an agent running as you can reach them. A required CI check, with evidence signed where the agent cannot reach, is what enforces. See where each control runs and how strong it is.

The core is free. A product for teams is launching soon.

There is no pricing yet.

Free, local core

For one developer

  • The use05 command line tool, the runner and the receipt format.
  • Policy, a signed organisation minimum, and folder and file rules.
  • Open source under Apache-2.0.
On our roadmap

05 for teams

  • A simple web layer for managing how your team works in its code.
  • Shared policy and an approval inbox.
  • Audit history and SSO.
  • Handles metadata only, never your code.

Several agents, one codebase, no collisions

Run as many agents as you like. 05 coordinates them so they do not overwrite each other's work. How it keeps them apart.

Each agent claims an area

An agent declares where it will work before it starts, and that area is reserved for it.

The others are told

If another agent plans or edits inside that area, it is told who holds it and why, both when it plans and at every edit. Your policy can make it ask a person, or refuse.

Each change lands on its own

Every agent works on its own branch and worktree. A change lands only exactly as it was checked, then its branch and worktree are cleaned up.

Your agents, your Git host

Claude Code and Codex

Currently supported by 05, through hooks that watch the session. Details.

Any other agent

Works through a generic hook. The git pre-push gate and the CI template check every change, whoever wrote it.

GitHub first

05 works with any Git host and starts with GitHub. The host only enforces, so you can switch hosts. 05 does not try to become one.

Common questions

More on the FAQ page.

Do I still need pull requests?

No. You approve, run use05 land and push. Pull requests still work if your team wants them.

Does 05 use an AI to judge my code?

No. Fixed rules compare the declared plan with what changed and check the signed evidence. The same change always gets the same answer.

What happens if 05 itself breaks?

It gets out of the way and tells you. A failure is always shown, never reported as a pass.

Try 05 on your own repositories

The source, install steps and docs are on GitHub. Have a question, or want to tell us which agent and Git host you use? Email us. No forms, no cookies.

View on GitHub [email protected]