decionisdecionis/agent-safe-pipeline/AGENTS.md

agent-safe-pipeline

AGENTS.md672 starsChanged yesterdayApache-2.0View on GitHub

AgentSafe is the execution gateway: an agent sends its action through AgentSafe, Decionis decides ALLOW, ESCALATE or BLOCK, and only an allowed action runs, once, on a single-use grant. AgentSafe decides nothing itself. The Decionis guides for policy authoring, AgentSafe implementation and workflow setup are installed with npx @decionis/mcp context install --client <claude|codex|copilot|kiro|cursor> from the same source as the Decionis repository. Reinstall to update them; never hand-edit them.

Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,439 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository10 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- .cursor/rules/AgentSafeImplementation.mdcCursor rule
- .cursor/rules/PolicyAuthoring.mdcCursor rule
- .cursor/rules/WorkflowSetup.mdcCursor rule
- llms-full.txtllms.txt
- llms.txtllms.txt
- agentsafeSkill
- policyauthoringSkill
- workflowsetupSkill
- Decionis Commerce GateSkill

The file

We split this AGENTS.md into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Never rename the wire verdicts ALLOW, ESCALATE and BLOCK.
line 14
Distinctive:
Commit with a DCO sign-off: git commit -s.
line 15
Very specific:
Use Node 22.14 or later (.nvmrc) and pnpm 9.15.3.
line 17
Distinctive:
Never commit keys, tokens or customer payloads.
line 19

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

AGENTS.md

AgentSafe repository

AgentSafe is the execution gateway: an agent sends its action through AgentSafe, Decionis decides ALLOW, ESCALATE or BLOCK, and only an allowed action runs, once, on a single-use grant. AgentSafe decides nothing itself.

Layout

packages/pipeline (@decionis/agent-safe-pipeline): SafeExecutor, ActionRegistry, intent capture, the Decionis gate and grant verifier.
packages/agentsafe (@decionis/agentsafe): the Gateway, adapters and the CLI.
spec/: versioned contracts such as agent-safe.executors.native/1 and agent-safe.intent/1.
govern/: govern init, which writes a shadow-mode CI workflow and DECIONIS_POLICY.md.

Rules

Never rename the wire verdicts ALLOW, ESCALATE and BLOCK.
Commit with a DCO sign-off: git commit -s.
Let the pre-commit hook run the whole gate (pnpm precommit); never bypass it.
Use Node 22.14 or later (.nvmrc) and pnpm 9.15.3.
Push branches only. The Decionis bot opens the pull request.
Never commit keys, tokens or customer payloads.

Guides for AI assistants

The Decionis guides for policy authoring, AgentSafe implementation and workflow setup are installed with npx @decionis/mcp context install --client <claude|codex|copilot|kiro|cursor> from the same source as the Decionis repository. Reinstall to update them; never hand-edit them.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free