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-profilegit 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-profile)<a href="https://agentmods.dev/commands/zircote/human-voice/voice-profile"><img src="https://agentmods.dev/badge/commands/zircote/human-voice/voice-profile.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 | $0.00011 | $0.01282 |
| Opus 5 | $0.00005 | $0.00641 |
| Sonnet 5 | $0.00002 | $0.00256 |
| Haiku 4.5 | $0.00001 | $0.00128 |
Grade A, and why
voice-profile 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/voice-profile — View a Completed Voice Profile
Display the full voice profile with dimension scores, calibration, distinctive features, and the user's own writing samples as example prose.
Procedure
-
Identify session: If a session ID argument is provided, use it. Otherwise, find the most recent session with
stateofcompleteviabin/voice-session list. -
Validate: Load
state.jsonviabin/voice-session load {session_id}. If state is notcomplete, inform the user and suggest/voice-resume. -
Read profile: Load
{session_dir}/profile.json. -
Display formatted profile:
Do NOT load or display interview writing samples. Interview responses are internal data for the scoring and NLP pipelines. The Example Prose section is always generated fresh from the profile configuration to demonstrate what the plugin produces under this profile's rules.
═══════════════════════════════════════════════════ VOICE PROFILE Session: a1b2c3d4-... Writer: business_professional ═══════════════════════════════════════════════════ Identity: A direct, analytical voice that favors precision over warmth. Writes in structured, medium-length sentences with minimal hedging. ── Gold Standard Dimensions ───────────────────── Dimension Self Observed Composite ───────────────────────────────────────────────── Formality 65 58 62 Emotional Tone 35 41 38 Personality 75 67 71 Complexity 50 60 55 Audience Awareness 80 76 78 Authority 74 70 72 Narrativity 40 48 44 Humor 35 25 30 ── Semantic Differential ──────────────────────── Formal ●●●●○○○ Casual (4.2) Assertive ●●●●●○○ Tentative (5.4) Direct ●●●●●●○ Diplomatic (5.8) Structured ●●●●●●○ Flowing (5.6) Concrete ●●●●●○○ Abstract (5.1) ── Calibration ───────────────────────────────── Overall self-awareness: 0.76 High awareness: formality, audience_awareness Blind spots: complexity, humor Aspirational gaps: humor: current 30 → desired 50 (Δ20) ── Distinctive Features ───────────────────────── - High use of em-dashes for parenthetical asides - Low hedging frequency (boost-to-hedge ratio: 2.3) - Active voice dominance (87% of clauses) - Topic-first paragraph structure - Preference for Germanic over Latinate vocabulary ── Voice Stability ───────────────────────────── Stable across contexts: formality baseline, sentence length range, punctuation habits Adapts by context: emotional tone, humor level, vocabulary sophistication ── Example Prose ──────────────────────────────── SPONTANEOUS (email declining invitation): Thanks for thinking of me, but I'm going to have to pass on Saturday. I've got a deadline Monday that's going to eat the whole weekend. Let's find another time — maybe the following week works better for both of us. REFLECTIVE (place description): The library in my college town had this particular corner on the second floor where the afternoon sun would hit the oak table just right. It smelled like old paper and floor wax. I spent four years at that table, and most of what I know about thinking carefully I learned there. PROFESSIONAL (decision explanation): We decided to sunset the legacy API because maintaining two parallel interfaces was costing us roughly 30% of the backend team's time. The new API covers all the same use cases with better documentation and faster response times. ═══════════════════════════════════════════════════
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 · 120 lines · 11 tokens per session scan A 76b2add031fa
voice-profile is a command published in the GitHub repository zircote/human-voice (10 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 1,282 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/.
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.