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/clever-cc-plugins/cc-content/humanizenpx skills add clever-cc-plugins/cc-content --skill humanizegit clone --depth 1 https://github.com/clever-cc-plugins/cc-contentWhat 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 | $0.00134 | $0.02837 |
| Opus 5 | $0.00067 | $0.01418 |
| Sonnet 5 | $0.00027 | $0.00567 |
| Haiku 4.5 | $0.00013 | $0.00284 |
Grade A, and why
humanize 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 2d 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Humanize Skill
You are helping the owner remove AI "tells" from an existing draft and produce a
version that reads as genuinely human-written, calibrated to the company's brand
voice. This skill takes any draft regardless of origin — it is not limited to
drafts produced by other cc-content skills.
This skill is format-, language-, industry-, and audience-neutral. It carries the detection and rewrite craft below but calibrates every stylistic choice to the loaded brand voice — a formal-voice project and a casual-voice project get different rewrites of the same input.
Step 0: Recall learnings
If .claude/learnings.md exists, read it silently. Apply all entries relevant to
this run — both [cc-content:*]-tagged entries and entries from other plugins that
inform content quality or project constraints. Do not announce this step. If the
file is absent, continue normally.
Step 1: Load context
Read the context table from all loaded CLAUDE.md files:
grep -A 200 '## Context files' CLAUDE.md 2>/dev/null || echo "(no context table)"
CLAUDE.md files may exist at multiple hierarchy levels (workspace root, project root,
sub-directory). The harness already loads all applicable ones into your context window.
If multiple ## Context files tables exist, rows from more specific CLAUDE.md files
take precedence over less specific ones.
If no context table is found in any loaded CLAUDE.md, ask once:
"I don't see any context files registered. Would you like to: (a) Pause and run
/content-onboardingto set up context (b) Continue without project context (humanization will use generic style choices)"
Stop if (a); note "generating without project context" and continue if (b).
If a context table exists, read every file listed in the File column, and identify which one covers brand voice (writing style, tone, vocabulary, phrasing rules, things to avoid) by matching against each file's Summary entry — this is the only need this skill gates on. Organization background, audience, and output language are noted silently if present and never block — humanization revises style, not substance, so it doesn't need them to do its job.
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.
- 2d ago First seen · 250 lines · 134 tokens per session scan A 502cf460a215
humanize is a skill published in the GitHub repository clever-cc-plugins/cc-content (1 stars, last pushed 7d ago), licensed MIT. It adds 134 tokens to every session and 2,837 once invoked, about $0.0007 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
auditing-config
Audit and optimize an existing Claude Code configuration against current best practices. Use this skill when a user asks to review, improve, clean up, or optimize their Claude Code setup, CLAUDE.md, settings, hooks, MCP servers, or skills. Also use when the user says things like "check my config", "is my CLAUDE.md too…
feature-radar-scan
Discover new feature opportunities from creative brainstorming, user feedback, ecosystem trends, and cross-project research. Writes results to .feature-radar/opportunities/. MUST use this skill when the user wants to GENERATE new ideas — not evaluate existing ones. Trigger on any request to brainstorm, explore…
feature-radar
Full-cycle feature discovery, evaluation, and prioritization. Builds a persistent knowledge base at .feature-radar/ and runs a 6-phase workflow to recommend what to build next. Modes: full (all phases), quick (scan only), evaluate (prioritize), #N (deep-dive one). MUST use this skill whenever the user asks about…
feature-radar-archive
Archive a completed, rejected, or covered feature into .feature-radar/archive/ with mandatory learning extraction. MUST use this skill whenever a feature reaches a terminal state — done, rejected, covered, deferred, or N/A. Even casual mentions like "we shipped X" or "X is done" should trigger this. The skill extracts…
feature-radar-ref
Record external observations, ecosystem trends, and creative inspiration into .feature-radar/references/. MUST use this skill when the user mentions something interesting from outside their project — other tools, articles, approaches, or trends. Even casual mentions like "I saw a cool thing in X" should trigger this…
feature-radar-learn
Extract reusable patterns, architectural decisions, and pitfalls from completed work into .feature-radar/specs/. Captures the "why" behind choices so future sessions build on past experience. MUST use this skill when the user reflects on what worked/didn't, wants to document a decision, or mentions remembering a…