How many of the spec's requirements were verified for this tool. See /coverage for the full matrix.
Level
Total
Verified
Unverified
MUST
28
19
9
SHOULD
21
13
8
MAY
10
10
0
Audience signal: mixed
This tool sends mixed signals: some agent-readable affordances are present, others are not. Treat the warnings below as friction points, not defects.
This is an informational signal, not an authoritative verdict — see methodology. The per-audit evidence below is the ground truth.
Top Issues
FAILEach subcommand's `--help` ships at least one invocation exampleProgressive Help Discoverysubcommands missing example invocations in their `--help`: aliases, chat, collections, embed, embed-models, fragments, install, keys, logs, models, openai, plugins, schemas, templates, tools, uninstall. Examples teach agents the call shape faster than option tables; use clap's `after_help` or a dedicated `Examples:` block.
WARNVersion flag works (`--version` plus short alias)Progressive Help Discovery`--version` works but no short alias responded (tried -V, -v, -version). Adding one shortens version probes for agents.
WARNVersion flag works (`--version` plus short alias)Progressive Help Discovery`--version` works but no short alias responded (tried -V, -v, -version). Adding one shortens version probes for agents.
target satisfies P1 via alternative gate (help-on-bare or stdin-primary)
WARN
Flags advertise env-var bindings in --help
2 flag(s) found in --help but no `[env: NAME]` bindings advertised
PASS
Secret-bearing flags expose stdin or *-file companion
WARN
`--help` advertises default values for flags
no default-value annotations found in --help. SHOULD-tier — agents reading help text need to see what value a flag falls back to when omitted (`[default: <value>]` per clap convention).
WARN
Rich-TUI affordance for TTY contexts
no rich-TUI affordance detected (no `--tui`/`--interactive`/`--ui` flag, no spinner/progress/tui mention in --help). MAY-tier — rich TUI in TTY contexts is a nice-to-have, not required.
`--version` works but no short alias responded (tried -V, -v, -version). Adding one shortens version probes for agents.
WARN
Version flag works (`--version` plus short alias)
`--version` works but no short alias responded (tried -V, -v, -version). Adding one shortens version probes for agents.
WARN
`examples` subcommand or `--examples` flag for curated usage patterns
no `examples` subcommand or `--examples` flag found. MAY-tier — a curated usage block keeps agents from hunting through long help text.
WARN
Short `-h` summary differs from `--help` long form
`-h` and `--help` produce byte-identical output. SHOULD-tier — clap renders the short summary on `-h` and the full description on `--help` when `long_about` is set; collapsing them gives agents no concise list-level grep target.
FAIL
Each subcommand's `--help` ships at least one invocation example
subcommands missing example invocations in their `--help`: aliases, chat, collections, embed, embed-models, fragments, install, keys, logs, models, openai, plugins, schemas, templates, tools, uninstall. Examples teach agents the call shape faster than option tables; use clap's `after_help` or a dedicated `Examples:` block.
WARN
Help text pairs human and `--output json` example invocations
no paired text + `--output json` example found within 5 lines in top-level or any subcommand `--help`. Pairing keeps agents from reverse-engineering the JSON invocation from the text one.
no `--color` flag advertised. MAY-tier — `auto|always|never` lets agents and pipelines override the TTY-based default.
SKIP
Input-accepting commands read from stdin when no file is given
no input-accepting subcommand detected (process/parse/convert/transform/analyze/validate/format/lint/audit); vacuous skip for the conditional SHOULD.
WARN
Subcommand naming follows a consistent verb/noun convention
subcommand naming is inconsistent: 7 non-verb subcommand(s) (aliases, collections, fragments, keys, logs, schemas, templates) mix verb and non-verb children at the second level, so an agent cannot predict where the action lives. SHOULD-tier: pick a consistent shape (all verb-first, all noun-verb hierarchy, or any combination where each non-verb group's children are uniformly verbs). The verb list is a heuristic; inspect `--help` to confirm.
no `--verbose` / `-v` flag advertised. SHOULD-tier — agents debugging failures need a way to escalate diagnostic detail.
SKIP
`--limit` / `--max-results` flag for list operations
no list-style subcommand detected (list/ls/search/query/find/show/get); vacuous skip for the list-only SHOULD.
SKIP
Cursor-based pagination flags for list traversal
no list-style subcommand detected; vacuous skip for the list-only MAY.
SKIP
`--timeout` flag for long-running operations
no long-running subcommand detected (serve/daemon/watch/tail/monitor/follow/run/start/stream); vacuous skip for the conditional SHOULD.
WARN
Help text advertises TTY-aware verbosity behavior
no TTY-aware language found in `--help`. MAY-tier — automatic verbosity reduction when stdout is piped or redirected lets agents skip the explicit `--quiet` flag. Behavioral probes cannot simulate a real TTY without a pty crate, so this audit relies on documented intent.
Skill bundle has install path (`tool skill install [<host>]`)
PASS
`skill install --all` for multi-runtime install
PASS
`skill update` / `skill upgrade` for bundle refresh
Details
Version scored
0.31
Audit date
2026-06-01 17:36:00 UTC
Duration
16.4s
Platform
linux/x86_64
Mode
command
Anc build
0.5.0
Install
brew install llm
Embed the badge
The badge floor is 70%; this scorecard is at 68% (2 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 llm locally and inspect the failing audits:
anc audit --command llm --output json
Install anc first if you don't have it. Add --output json to get the same JSON shape committed under scorecards/.