3 findingsStatic scanned
Runs OpenAI's Codex coding agent locally on your computer from the command line.
71.3M installs/moApache-2.0
Aclif Core
aclif · Agent
aclif is a command-line framework built for AI agents rather than people. Every provider it ships gets the same grammar, JSON reply and error vocabulary, and alias sets map names across systems, so a customer can resolve to an Account in Salesforce or a company record in ServiceNow. Commands can describe themselves before they run, without credentials or API calls, and the runtime can be embedded in a host that supplies credentials, identity and policy. Running commands for real needs credentials for each provider you use.
Written by ooruby from the README of @aclif/core 1.4.0.
Not claimed by its maker. Is this yours? Prove it and answer the findings
Why it's useful
Your agent learns one command grammar and one error vocabulary and can then work across several SaaS platforms.
What you could do with it
- Run the discover command to see which providers are configured, then ask for a briefing on one, such as Salesforce.
- Inspect a command's schema and runnable examples first, with no credentials needed and no API calls made.
- Preview a change with a dry run, confirm it where required, and read the audit line written after each run.
Written from its documentation: what it says it can do, not what our checks found.
What else was checked
Publisher and name
Nothing found across 5 checks run. Checked 2026-10-11.
Maintenance
MaintainedLast release 25 Sep 2026 (1.4.0), 15 days before this check on 11 Oct 2026.
Read from the npm registry's publish history, read by the nightly publisher check.
Release activity only: it says nothing about quality or safety, and a finished small package can be fine without releases. How it is measured
- Command execution is bounded
- inventory
- node child_process (lib/testing/run.js:20)
- node child_process (lib/core/credentials/secret-source.js:8)
- synchronous shell execution (lib/core/credentials/secret-source.js:40)
- An inventory of where the code starts another program, not a verdict on this row: whether each one runs a fixed program or whatever it is handed takes a reading by hand.
- Tool description integrity
- nothing to read
- Pattern set 1.0 matched nothing on 2026-10-11, but none of the descriptions the package ships runs to 120 characters, so there was little for a rule to read.
- It reads the descriptions the package ships, not what the server says when it runs, and a clean description is not the same thing as a safe tool.
Published because it was found. A finding is information about where the limits are, not a verdict that the software is unsafe.
What this does not cover
- Everything. Treat it as you would software from anywhere else.
Tool descriptions are read with pattern set v1.0, published with every rule, its sources and how often it has been wrong.
Receipt history: every signed receipt for every version of this listing, and what changed between them.
In its maker's words
Agent CLI Framework: command-line tools for AI agents, one grammar and canonical names across every SaaS provider
Compare with
Compare all 4How far this has been checked
Static scanned
- What it establishes
- Its published package, or for a hosted server its source repository at a recorded commit, was read file by file, without running it, by every check in our current scan.
- What it does not
- How it behaves when it runs, or anything the scan does not read yet: several rubric checks, the repository's history, and compiled code in folders named dist or build. For a hosted server, that the endpoint runs the code that was read. The ooruby Index sets out exactly what was read.
- Exactly what was read
- Version 1.4.0, the file with digest sha512-okBfidGlfDhDgepoY1h2BS24kocjKJLu7L7ToWLT1nm0FglGRJb2tZNTpzL7YiDbnqmweR8bI2K0n/LG9BngHg==, as the registry publishes it. A published version cannot be replaced, so this names the same bytes for anyone who checks.
- Authentication
- Runs locally. No hosted endpoint is listed for this package. You run it on your own machine, so there is no endpoint of ours to authenticate against.
Adding it
Run it with:
npx -y -p @aclif/core@1.4.0 aclifPinned to 1.4.0, which is the version the findings above were found in. Drop the version to take whatever is newest, and the report on this page stops describing what you installed.
2,269 installs last month · build provenance signed · runs a script on install · no published advisories · version current · checked 2026-10-11
Where this came from
- Registry
- npm
- Package
- @aclif/core
- Version read
- 1.4.0
- Resolved
- 2026-10-10
Built from source, attested
npm publishes a signed statement that this exact package was built from the repository below, at this commit. It is verifiable without taking our word for it.
- Repository
- github.com/agent-cli-framework/aclif
- Commit
- 3b9d2f9ff2a4
- Built by
- github.com/actions/runner/github-hosted
- Registry publish attestation
- signed by npm · 2026-10-10
- Checked
- 2026-10-10
The badge, if this is your listing
It renders the current rung (static scanned) and links back here, where what that does and does not establish is one click away. It updates itself as the evidence deepens.
[](https://ooruby.com/market/aclif-core)About this listing
- Kind
- Agent
- Category
- Developer tools
- Pricing
- Free
- Sandbox
- No
- Hosted
- No
- Updated
- 2026-10-09
Similar agents
All agentsVerification records what our published tests found on a specific version at a specific date. It is not a warranty, and it does not certify that software is free of defects.