init

A quick setup command for teaching the coding agent how you write. It uses a short writing sample and a few corrections instead of a long questionnaire.

In plain words
What is it for?
Use it to create a personal writing profile and compare rewritten versions of text in different styles.
Why use it?
It avoids spending time filling out a detailed profile before seeing useful results. It also keeps sensitive information out of the setup sample.

Command

Install

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.

agentmods
npx agentmods add commands/nisus74/humanise/init
Clone the repo
git clone --depth 1 https://github.com/Nisus74/humanise
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 572 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00572
Opus 5 $0.00000 $0.00286
Sonnet 5 $0.00000 $0.00114
Haiku 4.5 $0.00000 $0.00057

Measured yesterday against content hash 282855896bc0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

init 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 yesterday.

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.

skill/commands/init.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

humanise: init

Set up the user's voice without making them complete a profile before seeing value.

Quick setup, about three minutes

  1. Resolve the private profile path. In a Claude Code marketplace plugin, use ${CLAUDE_PLUGIN_DATA}/profile; otherwise use the configured path or profile/ beside the skill. If it is missing, copy profile.template/ there. For a direct skill install, copy config.example.yml to config.yml beside SKILL.md.
  2. Ask the user to paste one short piece they wrote and like. A sent email, post, message or document paragraph is enough. Ask them to remove anything sensitive first.
  3. Ask what the sample was trying to achieve and who read it. Do not ask a long style questionnaire.
  4. If the user supplied text to improve, create up to three versions:
    • close: minimal change;
    • direct: point and ask moved forward;
    • conversational: warmer and closer to speech.
  5. Ask which version is closest and what they would change. The choice and correction are stronger evidence than abstract style adjectives.
  6. Save the original sample as profile/sample-<channel>-<slug>.md using SAMPLE_TEMPLATE.md.
  7. Write the observed decisions to profile/voice-decisions.md with provisional confidence. Record any rejected moves in profile/negative-examples.md.
  8. Fill only the known fields in profile/identity.md and config.yml. Leave unknowns explicit.

At this point, produce a useful personalised draft. Do not block on a full fingerprint.

Deeper setup, offered after value is visible

When the user wants better coverage:

  1. Use scripts/corpus-questionnaire.md to collect five to ten real samples across the channels they actually use.
  2. Write profile/soul.md from concrete convictions, not generic values.
  3. Keep profile/absolute-rules.md to explicit non-negotiables. Do not install engine defaults as personal absolutes.
  4. Run scripts/generate-fingerprint.md to build profile/voice-fingerprint.md. Label every pattern confirmed, supported or provisional and name its evidence.
  5. Add relationship-specific differences to profile/relationships.md only when direct evidence supports them.

Read the full file on GitHub · 49 lines

Changes

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.

  1. yesterday First seen · 49 lines · 0 tokens per session scan A 282855896bc0

Subscribe to this mod's changes

init is a command published in the GitHub repository Nisus74/humanise (1 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 572 tokens. 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.