Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/zircote/human-voice/voice-copilot-installgit clone --depth 1 https://github.com/zircote/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-copilot-install)<a href="https://agentmods.dev/commands/zircote/human-voice/voice-copilot-install"><img src="https://agentmods.dev/badge/commands/zircote/human-voice/voice-copilot-install.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 | $0.00013 | $0.00832 |
| Opus 5 | $0.00006 | $0.00416 |
| Sonnet 5 | $0.00003 | $0.00166 |
| Haiku 4.5 | $0.00001 | $0.00083 |
Grade A, and why
voice-copilot-install 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 5d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/human-voice:voice-copilot-install
Install one or more human-voice profiles into a target project as GitHub Copilot custom instructions, prompts, agents, AGENTS.md, and a PR review workflow.
Arguments
$ARGUMENTS — optional CLI args forwarded to bin/voice-copilot-install.
Examples:
--target /path/to/repo(default: current working directory)--profile robert-allen(single profile; default: active profile)--profiles robert-allen,tech-authority --route 'docs/**=tech-authority;**/*.md=robert-allen'--default robert-allen(which installed slug is the repo default)--overwrite error|merge|force(default:merge— replaces marker blocks, preserves surrounding content)--dry-run(print intended writes, touch nothing)--no-workflow,--no-prompts,--no-agent,--no-agents-md,--no-redact
If $ARGUMENTS is empty, run with defaults (active profile, install into cwd, merge mode).
Steps
Important: always invoke the CLI via its absolute path at ${CLAUDE_PLUGIN_ROOT}/bin/voice-copilot-install. The default --target=. resolves against the user's current working directory (the project they're standing in), which is what you want. Do NOT cd into the plugin root first — that would make --target=. resolve to the plugin itself.
-
Run:
"${CLAUDE_PLUGIN_ROOT}/bin/voice-copilot-install" $ARGUMENTS. Surface the list of written/skipped files. If the user passed--dry-run, the CLI will print intended writes and touch nothing — do not follow up with a real install unless they ask. -
Report: Summarise what was written and point the user at
.github/copilot-instructions.mdas the entry point. If a workflow was written, remind them to commit and push so Copilot code review picks it up on the next PR.
What gets written
.github/copilot-instructions.md— repo-wide, loaded by Copilot automatically on GitHub.AGENTS.mdat repo root — coding-agent instructions..github/instructions/human-voice-<slug>.instructions.md— path-scoped (one per profile;applyToglob drives routing)..github/prompts/voice-{review,fix,draft}.prompt.md— reusable Copilot Chat slash commands..github/agents/human-voice-<slug>.agent.md— Copilot custom agents (one per profile)..github/human-voice/<slug>/profile.json+voice-prompt.txt— redacted profile artefacts..github/human-voice/scripts/*.js— bundled validator scripts..github/workflows/voice-review.yml— PR workflow that runs validators on changed prose and comments findings.
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.
- 5d ago First seen · 51 lines · 13 tokens per session scan A e9891ddfb9fb
voice-copilot-install is a command published in the GitHub repository zircote/human-voice (10 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 832 once invoked, about $0.0001 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.
reindex
Idempotent reindex of an existing course — rewrite retired coverage.md tier markers to canonical vocabulary and materialize errors/log.md nature/phase into the on-disk schema (header keys == data keys), in place and atomically, WITHOUT running analyze.
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.
blind
Strategy-level blind drill on a known HW or example problem. User describes approach in prose (no math typing); Claude verifies against solution then saves clean reference to derivations/.
doctor
Diagnose the paideia install + course workspace (Python, poppler, tesseract, Ollama/Qwen3-VL, course folders, .course-meta, writable paths, statusline wiring) and optionally auto-repair the permission-free issues. Run when a command won't work or right after cloning.
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.