Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add zircote/human-voice/plugin install human-voiceWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/zircote/human-voice/voice-review)<a href="https://agentmods.dev/commands/zircote/human-voice/voice-review"><img src="https://agentmods.dev/badge/commands/zircote/human-voice/voice-review.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00009 | $0.01419 |
| Opus 5 | $0.00005 | $0.00709 |
| Sonnet 5 | $0.00002 | $0.00284 |
| Haiku 4.5 | $0.00001 | $0.00142 |
Grade A, and why
voice-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Human Voice Review
Analyze content for AI-generated writing patterns using a multi-tier approach.
Options
--ignore=emojis,em-dash- Skip specific pattern categories during character detection- Valid categories:
emojis,em-dash,en-dash,smart-quotes,ellipsis,bullet,arrow - Example:
/human-voice:voice-review --ignore=emojis,arrow docs/
- Valid categories:
Step 0: Load Configuration and Voice Profile
ALWAYS run this before any analysis. Not optional.
!cat "$HOME/.human-voice/config.json" 2>/dev/null || echo "NO_CONFIG"
!cat "$HOME/.human-voice/profile.json" 2>/dev/null || echo "NO_PROFILE"
Use detection.content_directories to resolve targets when no path is given. Use detection.extensions to filter file types. Use detection.ignore to skip directories. If a voice profile loaded, use it to calibrate Tier 3/4 against the user's actual voice.
Step 1: Resolve Target
$IF($1,
Review target: $1
Verify the path exists:
!test -e "$1" && echo "Path exists: $1" || echo "ERROR: Path '$1' does not exist"
,
No target specified. Resolving from config...
!python3 -c "import json,os,sys; p=os.path.expanduser('~/.human-voice'+'/config.json'); c=json.load(open(p)); dirs=[d for d in c.get('detection',{}).get('content_directories',[]) if os.path.isdir(d)]; print(' '.join(dirs)) if dirs else sys.exit(1)" 2>/dev/null && echo "(from config.json)" || ls -d _posts content _docs docs 2>/dev/null || echo "No content directories found"
)
Step 2: Character-Level Detection
Run automated character validation:
$IF($1,
!node "${CLAUDE_PLUGIN_ROOT}/skills/human-voice/scripts/validate-character-restrictions.js" $ARGS 2>&1 || true
,
!dirs=$(python3 -c "import json,os,sys; p=os.path.expanduser('~/.human-voice'+'/config.json'); c=json.load(open(p)); dirs=[d for d in c.get('detection',{}).get('content_directories',[]) if os.path.isdir(d)]; print(' '.join(dirs)) if dirs else sys.exit(1)" 2>/dev/null || { for d in _posts content _docs docs; do test -d "$d" && printf '%s ' "$d"; done; }); test -n "$dirs" && node "${CLAUDE_PLUGIN_ROOT}/skills/human-voice/scripts/validate-character-restrictions.js" $dirs $ARGS 2>&1 || echo "No content directories found to validate"
)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 102 lines · 9 tokens per session scan A dcb56432e1ea
voice-review is a command published in the GitHub repository zircote/human-voice (10 stars, last pushed 1mo ago), licensed MIT. It adds 9 tokens to every session and 1,419 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
graph
Extract prerequisite concept graph from converted course materials and write course-index/concept-graph.md.
alt
Import an Exam Radar (OPTIMETA Alt plugin) export and fold its lecture-emphasis exam signal into the course index — radar.md, a lecture-emphasis column on coverage.md, and a gold-zone weakmap.
quiz
Generate N practice problems on a topic. Saves problem MD + hidden answer MD. User solves on paper, uploads answer PDF, then runs /grade. First arg weakmap → auto-load latest weakmap report and target its top weaknesses.
weakmap
Priority-ranked weakness report. No arg → fresh report from latest errors per pattern. With concept arg → patch latest report by adding the user-declared weakness, save as new timestamped file.
derive
Save a clean reference derivation of a target equation or theorem to derivations/. Draws from course materials (textbook, lecture notes) rather than testing the user.
mock
Generate a mock exam matched to the course's structure (inferred from course-index). Saves problem MD + hidden solution MD. User solves on paper, uploads PDF, runs /grade.