What does MARGINAL do?

MARGINAL observes AI coding-agent actions and looks for repeated successful work where the observable workspace state and evidence have not changed.

Does MARGINAL block AI agents immediately?

No. MARGINAL starts in Shadow Mode. Its Codex integration can earn narrowly scoped Tool Enforcement only after local evidence and explicit promotion.

Does MARGINAL claim to save 24.93% of tokens?

No. A historical three-task exploratory smoke observed a 24.93% token difference, but neither lane resolved a task and no deny was applied, so the difference is not attributed to MARGINAL.

Runtime governor for AI coding agents

AI agents repeat work that changed nothing.MARGINAL catches it.

MARGINAL watches tool actions, outcomes and workspace evidence. When the same successful action repeats with no observable progress, it can identify the loop — without assuming every retry is waste.

Observe first. Prove waste. Earn enforcement.

★ Star MARGINAL on GitHub Watch the mechanism ↓

Open source
Local first
Provider neutral
Zero mandatory runtime dependencies

agent trace / workspace

Read config.pynew evidence acquired

RUN

Read config.pyverification; outcome successful

RUN

Read config.pysame workspace state · no new evidence

OBSERVE

Read config.pyexact eligible no-progress repetition

STOP*

*Only after local Earned Enforcement. Otherwise MARGINAL stays advisory.Fails open on ambiguity.

10-second mechanism demo

Activity is not the same thing as progress.

Same action. Same state. No new evidence. That is the signal MARGINAL cares about. This deterministic visual is a mechanism demonstration, not a production benchmark.

Without a governorLOOP

01Read config.pyRUN

02Read config.pyRUN

03Read config.pyRUN

04Read config.pyRUN

05Read config.pyRUN

With MARGINALEVIDENCE

01Read config.pyNEW EVIDENCE

02Read config.pyVERIFY

03Read config.pySAME STATE

04Read config.pySTOP CANDIDATE

05Earned authority?BLOCK / ALLOW

Open shareable demo ↗No API credits required. No provider telemetry claimed.

How it works

A governor that has to earn the right to govern.

Installation does not equal authority. MARGINAL separates observation, proof and enforcement so an efficiency tool cannot casually become a correctness risk.

01 / OBSERVE

Watch

Collect derived action, outcome, coverage, workspace-state and evidence signals locally.

02 / PROVE

Compare

Look for repeated successful actions where observable state and useful evidence did not change.

03 / EARN

Build trust

Require representative local evidence, clean coverage and explicit promotion before blocking.

04 / INTERVENE

Stop narrowly

Only eligible action families can be denied, and only under the exact proven no-progress condition.

05 / RECOVER

Fail open

Unknown outcomes, drift, integrity failures or changed evidence remove pressure and restore allowance.

Works alongside coding agents

One governance core. Conservative engine boundaries.

MARGINAL is not another coding agent. It sits beside supported runtimes and turns native lifecycle signals into the same provider-neutral evidence model.

Tool Enforcement

Codex

Native plugin. Shadow Mode by default; repository-local Earned Enforcement is intentionally narrow.

Observe-only

Claude Code

Native hooks record engine-declared success and failure without changing the next model action.

Observe-only

OpenCode

In-process JavaScript plugin with a persistent stdio bridge to the provider-neutral runtime.

Observe-only

PrivacyCode

OpenCode-compatible target with its own engine identity, ledger root and trust evidence.

Designed to be falsifiable

MARGINAL has to justify its own overhead, too.

The project treats governance cost, harmful interventions and preserved quality as first-class measurements — not footnotes.

Shadow first

New installations observe before blocking. Lack of evidence is not permission.

Decision ledger

Canonical records are hash chained so decisions can be reproduced and integrity drift detected.

Local-first privacy

Raw prompts, source, commands, outputs, transcripts and credentials are not evidence fields.

Fail open

Ambiguous or unsupported outcomes do not become evidence for blocking.

Explicit boundaries

Tool Enforcement is not presented as Full Compute Enforcement. Capabilities stay adapter-specific.

Graceful irrelevance

If a future agent is already efficient, MARGINAL should measure that and get out of the way.

Public evidence, without marketing math

The first smoke validated the integration — not the savings claim.

We keep negative and inconclusive results public because MARGINAL's credibility depends on separating observation from causation.

Exploratory SWE-bench Lite smoke

Exploratory 3-task smoke, one paired run per task. Both lanes resolved 0/3. No deny was applied in these three agent trajectories. A 24.93% token difference was observed, so the difference is not attributed to MARGINAL and is not a support claim.

The full report, raw JSON, protocol and evidence bundle remain public in the repository.

Read public report ↗Inspect raw evidence ↗

Resolved0/3 → 0/3

Effective tokens24.93% fewer

Tool calls3.03% fewer

Governance latency7.06 s

Applied denies0

Evaluatorpass_through

Install

Start in Shadow Mode.

The Codex marketplace install is one command. Enforcement still has to be earned locally.

codex plugin marketplace add SignalLayerLabs/Marginal --ref main && codex plugin add marginal@marginal

Remove cleanly with codex plugin remove marginal@marginal.

Research & Engineering

Ideas that have to survive contact with evidence.

Long-form technical notes on no-progress detection, runtime governance, privacy boundaries and the cases that could prove MARGINAL wrong.

Detecting no-progress without reading prompts

Use action identity, outcomes, observable state and evidence without turning every repeated call into waste.

Why an AI agent governor should start powerless

Installation is not evidence. Observe first, earn narrow authority, and demote when assumptions drift.

Read Research & Engineering →

Technical guides

Search the problem. Inspect the mechanism.

Evidence-first guides for developers dealing with repeated reads, tool calls and no-progress loops in coding agents.

No-progress loops

Detect successful activity that repeats without observable progress.

Repeated tool calls

Separate useful verification from same-state repetition.

Codex

Shadow-first native plugin with narrow evidence-earned Tool Enforcement.

Claude Code

Observe-only hooks with engine-declared outcomes and no blocking.

Explore all guides →

FAQ

Fast answers before you clone.

What does MARGINAL actually stop?

Today, Codex Tool Enforcement is deliberately narrow. Exact eligible workspace-local reads can become denyable after verified repeated success with no state or evidence change. Generic shell, tests, search, writes, network and unknown MCP paths remain observe/recommend only.

Is MARGINAL a security product?

No. It is an efficiency governor, not a security boundary against software running as the same OS user.

Does it work with Claude Code?

Yes in Observe-only mode. Claude Code hooks can record engine-declared success/failure and feed the same evidence model, but the integration does not block actions today.

Why not just cap tokens?

A fixed cap cannot distinguish useful verification from repeated no-progress work. MARGINAL focuses on the marginal value of the next action and on observable evidence, not only the size of a budget.

Open source · Apache-2.0

If your coding agent loops, make the loop prove it is useful.

Clone it, inspect the hooks, run Shadow Mode, challenge the evidence model — and star the repo if you want this idea to keep moving.

★ Star MARGINAL Quickstart ↗