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 skills/nisus74/humanise/skillnpx skills add Nisus74/humanise --skill skillgit clone --depth 1 https://github.com/Nisus74/humaniseWrote 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/skills/nisus74/humanise/skill)<a href="https://agentmods.dev/skills/nisus74/humanise/skill"><img src="https://agentmods.dev/badge/skills/nisus74/humanise/skill.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 | $0.00112 | $0.02392 |
| Opus 5 | $0.00056 | $0.01196 |
| Sonnet 5 | $0.00022 | $0.00478 |
| Haiku 4.5 | $0.00011 | $0.00239 |
Grade A, and why
humanise 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 3d 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 — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
humanise
Produce writing a particular person would recognise as theirs. Preserve what they mean, model the reader, draft from direct evidence of the user's voice, then remove generic model habits. Clean prose is the floor. Voice fidelity is the goal.
Operating principles
Use this order when instructions compete:
- The user's current request.
- Meaning, factual fidelity and required wording.
- Direct samples from the same channel and relationship.
- Confirmed cross-channel voice evidence.
- The user's soul and absolute rules.
- Channel, register and dialect defaults.
- Generic anti-AI guidance.
Never change a claim to make the prose smoother. Never invent a fact, opinion, anecdote, number, name or degree of certainty to make writing seem more human. Never manufacture quirks to satisfy a style quota.
Modes
The host may invoke the skill explicitly or select it from the request. Interpret these optional mode words after the skill name:
init: run progressive voice setup.guide: draft new material.rewrite: edit existing material.check: inspect a draft for mechanical and structural tells.fingerprint: rebuild the voice model after new samples.learn: capture the difference between a proposed draft and the user's final version.improve: run the engine improvement workflow.
Read the matching file in commands/ when a mode is named. If none is named, infer guide,
rewrite or check from the request.
Boundaries
Apply the skill to prose the user will send, publish, present or approve. Hold off on:
- source code, configuration, identifiers and commands;
- quoted material and supplied testimonials;
- data tables and machine-readable formats;
- fixed legal, regulatory or contractual wording;
- the user's raw notes when they want those preserved as source material;
- conventional commit subjects.
Edit only the prose around exempt material. Preserve quoted spans exactly. Ask only when a wrong assumption would materially change the result.
What ships with it
58 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/adversarial-reviewer.md 3.4 KB
- agents/eval-generator.md 2.4 KB
- agents/fact-brief-checker.md 2.2 KB
- agents/improvement-proposer.md 2.4 KB
- agents/indistinguishability-judge.md 2.5 KB
- agents/openai.yaml 235 B
- CHANGELOG.md 30 KB
- commands/check.md 696 B
- commands/fingerprint.md 730 B
- commands/guide.md 679 B
- commands/improve.md 5.0 KB
- commands/init.md 2.5 KB
- commands/learn.md 3.3 KB
- commands/rewrite.md 740 B
- config.example.yml 791 B
- evals/assertions/mine_weaknesses.py 9.0 KB runs code
- evals/assertions/pairwise_trial.py 12 KB runs code
- evals/assertions/run_all.py 14 KB runs code
- evals/assertions/selftest.py 31 KB runs code
- evals/assertions/writing_checks.py 57 KB runs code
- evals/evals.json 9.0 KB
- evals/holdout-evals.json 3.9 KB
- evals/indistinguishability-log.md 1.6 KB
- evals/indistinguishability.md 5.9 KB
- evals/self-harness-loop.md 5.8 KB
- profile.example/absolute-rules.md 680 B
- profile.example/identity.md 787 B
- profile.example/README.md 765 B
- profile.example/soul.md 1.9 KB
- profile.template/absolute-rules.md 616 B
- profile.template/channels.md 519 B
- profile.template/CORPUS.md 1.5 KB
- profile.template/identity.md 579 B
- profile.template/negative-examples.md 492 B
- profile.template/register-descriptors.md 2.6 KB
- profile.template/relationships.md 393 B
- profile.template/SAMPLE_TEMPLATE.md 888 B
- profile.template/soul.md 1.2 KB
- profile.template/voice-decisions.md 666 B
- profile.template/voice-fingerprint.md 1.0 KB
- references/ai-slop-dictionary.md 26 KB
- references/channel-playbooks.md 29 KB
- references/cultural-calibration.md 7.6 KB
- references/dialect-en-AU.md 988 B
- references/dialect-en-GB.md 408 B
- references/dialect-en-US.md 778 B
- references/meaning-and-voice.md 4.3 KB
- references/mechanical-sweep.md 7.4 KB
- references/memory-loop.md 7.6 KB
- references/positive-patterns.md 9.9 KB
- references/structural-tells.md 27 KB
- references/technical-writing.md 7.6 KB
- references/tone-register.md 7.2 KB
- references/worked-examples.md 14 KB
- scripts/build_voiceprint.py 8.9 KB runs code
- scripts/capture_edit.py 7.1 KB runs code
- scripts/corpus-questionnaire.md 3.1 KB
- scripts/generate-fingerprint.md 3.6 KB
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.
- 3d ago First seen · 252 lines · 112 tokens per session scan A 2d322661a7de
humanise is a skill published in the GitHub repository Nisus74/humanise (1 stars, last pushed 7d ago), licensed MIT. It adds 112 tokens to every session and 2,392 once invoked, about $0.0006 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 skills, from other repositories
tdd-workflow
Test-driven development workflow.
collection
Choose which SkillNote skill collection is active for this Codex project. Use when the user says "change collection", "switch skills", "use frontend skills", or "show collections".
verify
Fact-check claims encountered during reading — dates, names, events, citations. Use when encountering historical facts or disputed claims.
expert
Base expert skill.
alpha
Alpha skill.
assistant
Assistant — on any repo, scan README→docs→AGENTS→CONTRIBUTING→PR templates→task runners→devcontainer→CI→configs before code; cite sources; prefer AGENTS.md for agent behavior; portable across Cursor/Copilot/Claude; use agent-toolkit CLI when needed.