Many coding agents. One set of rules.

Engineers choose the agent that performs best on their code, so most organizations end up running several. CompFly governs what those agents actually do, decides each call before it runs, and ships the same skills and instructions to all of them.

Claude CodeCursorGitHub CopilotVS CodeCodexGemini CLIWindsurfPiIn-house agents

Rules are written once. Every tool on this list follows them, and so does the next one a team picks up.

One decision, before the command runs.

An agent packaging a quarterly export tried to copy it to a bucket outside the org. It was not attacked. It was doing its job, and the fastest path ran through customer data.

agent     claude-code · repo payments-api · acting for m.okonkwo
call      Bash  aws s3 cp ./exports/customers_2026q3.csv s3://mk-scratch-2024/
matched   egress.external-bucket · pack platform-baseline v14
signals   destination outside org account · payload matched customer-PII · no egress grant
verdict   DENY  returned before the command ran
returned  "Use the approved export bucket in the org account. Loading skill: data-export."
record    entry 0x9c1f2a · signed

The denial goes back to the agent as a correction it can act on, so the work continues down the sanctioned path. And it is recorded against the agent, not the developer whose credentials it used. Downstream, the commit and the API call would both have named a person. The same holds for agents working unattended for hours, where nobody is watching a prompt and a bad call runs to completion.

From write to commit.

CompFly checks the work as it happens. The same rules cover what is unsafe and what is below standard.

When it writes code

Require a test with a new module. Keep a credential out of the file.

When it runs a command

Stop a destructive command before it runs. Check what it returned before the agent reads it.

When it commits

Hold it until the docs match and nothing is stubbed. Keep secrets out of the diff.

When it calls a model

Control what leaves the repository, and what it costs. Stop a user or team over budget.

Where the built-in controls stop.

Every coding agent now ships real enterprise controls, and they work. Each one governs its own tool.

What the agent may run

What each tool ships

Managed settings and permission rules set what commands and tools an agent can use, and cannot be overridden locally.

What remains

The rules bind that one tool. A second agent, or a script calling the model API directly, is governed by a different policy or none.

Sandboxing

What each tool ships

Sandboxed execution and network allowlists limit what a run can touch on the machine and reach on the network.

What remains

The sandbox covers the vendor’s own runtime. Headless runs in CI, and long jobs that work unattended for hours, often sit outside it.

Sensitive data

What each tool ships

Content exclusion and secret scanning keep named files and known secret patterns out of what the agent reads or commits.

What remains

Excluding a file is a decision made ahead of time. Whether this command, sending this payload, to this destination, should run is a decision made at the moment it happens.

Instructions and skills

What each tool ships

Instruction files and rules give each repository its own standing guidance for the agent.

What remains

They live per repository, edited by whoever is nearest. There is no org-wide version, no way to revoke one, and no record of which version an agent was carrying when it acted.

Spend

What each tool ships

Each tool reports its own usage and seats in its own console.

What remains

Nothing shows what a developer or a team costs across all of them, and nothing caps it. CompFly sets budgets per user and per team, applied at the model call.

Audit

What each tool ships

Each vendor logs its own sessions in its own schema, with its own retention.

What remains

The agent runs with a developer’s credentials, so downstream logs record the person, not the agent. Four tools produce four records that do not reconcile.

A team running four coding agents runs four sets of rules, four log formats, and no single record.

What the agents carry.

CompFly already sits in the path of every call. That is also how it delivers what those agents should know. One pack carries both halves: the skills and instructions they work from, and the controls for what they may do.

Versioned

Every call names the pack version that governed it, so the record shows what an agent was carrying when it acted, not only what it did.

Scoped

Assign a pack to a team, a repository, or a single agent. A payments repo carries more than a docs repo.

Revocable

Withdraw a skill or an instruction set and it stops being carried, without waiting on anyone to update a repo.
pack      platform-baseline  v14
assign    team:payments · repo:payments-api
carries   skill  data-export
          skill  incident-runbook
          rules  house-style, review-checklist
denies    egress.external-bucket
budget    250k tokens / dev / day
rollout   observe → enforce

Agents that carry the same instructions produce the same shape of work twice. A denial with a reason costs less than a merged mistake, and both cost less than a run the agent had to redo because nobody told it the house rules.

See what is running before setting a rule.

Setup takes an afternoon. Enforcement stays off until it is switched on.

Connect an existing channel

CompFly deploys through an existing MDM or identity provider. Developers do not change how they start an agent.

The inventory fills in

Every agent developers run, with its owner and repository. Token spend per tool and per team, and which skills get picked up.

Then publish a pack

One instruction set plus a small baseline of rules, scoped to a team or a repo. Observe only, so nothing is blocked.

Changes apply on the next call. And the first pack is not a blank page: CompFly ships a catalog of skills and baseline rules to adopt as they are, or edit to fit how teams work.

Four log formats become one, in the SIEM the security team uses.

Every entry names the agent that acted, the rule that allowed or stopped it, and the pack version in force at the time.

Bring us one team.

Connect one team. CompFly shows every coding agent they run, what it costs, and the calls a policy would have stopped, before anything is enforced.