anc.dev The agent-native CLI standard

shell-gpt

A command-line productivity tool powered by AI large language models

agent Python TheR1D/shell_gpt
57% pass rate
4/7 principles met

Spec Coverage

How many of the spec's requirements were verified for this tool. See /coverage for the full matrix.

Level Total Verified Unverified
MUST 23 9 14
SHOULD 16 0 16
MAY 7 0 7

Top Issues

All Checks

P1: Non-Interactive by Default

PASS Non-interactive by default
SKIP Non-interactive gate flag advertised in --help target satisfies P1 via alternative gate (help-on-bare or stdin-primary)
SKIP Flags advertise env-var bindings in --help target exposes no flags in --help

P2: Structured, Parseable Output

SKIP Structured output support no --output/--format flag detected

P3: Progressive Help Discovery

FAIL Help flag produces useful output --help exited with code 1
FAIL Version flag works --version exited with code 1

P4: Fail-Fast, Actionable Errors

PASS Rejects invalid arguments

P6: Composable, Predictable Command Structure

PASS Handles SIGPIPE gracefully
SKIP Pager-using CLI ships --no-pager escape hatch no pager signal (less/more/$PAGER/--pager) in --help
PASS Respects NO_COLOR

P7: Bounded, High-Signal Responses

WARN Quiet mode available no --quiet/-q flag detected in --help output

Details

Version scored
3.14
Audit date
2026-05-01 10:09:19 UTC
Duration
866ms
Platform
linux/x86_64
Mode
command
Anc build
0.3.0
Install
uv tool install shell-gpt

Embed the badge

The badge floor is 80%; this scorecard is at 57% (23 points below). Once the score clears the floor, the embed snippet will appear here. The top issues above are the place to start.

Reproduce this scorecard for shell-gpt locally and inspect the failing checks:

anc check --command sgpt --output json

Install anc first if you don't have it. Add --output json to get the same JSON shape committed under scorecards/.