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 skills add melodic-software/claude-code-plugins --skill write-for-humansgit clone --depth 1 https://github.com/melodic-software/claude-code-pluginsWrote 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/melodic-software/claude-code-plugins/write-for-humans)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/write-for-humans"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/write-for-humans/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/write-for-humans"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/write-for-humans.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00125 | $0.03483 |
| Opus 5.5 | $0.00050 | $0.01393 |
| Sonnet 5.5 | $0.00025 | $0.00697 |
| Haiku 4.5 | $0.00013 | $0.00348 |
Grade A, and why
write-for-humans 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 8d 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write For Humans
Why this skill exists
docs-hygiene:write-for-agents is the write-side doctrine for markdown an agent loads, and it
excludes human-facing prose deliberately, in its description and again in its own
"What this skill does NOT do": end-user READMEs, changelogs, and marketing prose "have a different
reader and different rules." This skill is those rules. The two are siblings on the same axis:
one moment (while the doc is being written), split by who reads the result.
Resolve the standard before you apply one
The project's own style guide wins. Always. Before writing, look for one, a STYLE.md, a
documentation contributing guide, a house standard named in the contributor docs, or a linter config
encoding prose rules. When the project declares a standard, it is authoritative and everything below
is a fallback you do not reach for. Say which one you resolved, in one line, before you write.
The layers below are a named default set, not this plugin's house rules. Each one settles a single question about the draft, and a finished draft has an answer to all four:
| Layer | Question it answers | Standard |
|---|---|---|
| Mode | Which kind of document is it? | Diátaxis |
| Address | How does a sentence speak to its reader? | Google developer documentation style |
| Load | How much does one sentence hold? | ASD-STE100 Simplified Technical English |
| Ambiguity | Can this be read two ways? | Global English |
A project that adopted a different guide, Microsoft's, Chicago, an in-house one, gets that guide, not these. A project with none gets these, and you say so, so the choice stays visible and the project can overrule it later. Never silently impose one.
Three rules that survive a declared guide
A project's own guide replaces everything else in this skill, but not these three. They concern doing the work rather than choosing a style, and no style guide asks a writer to keep empty words or to rename what is being documented. Apply them under whatever standard you resolved. In the rare case a project's guide contradicts one of them, the project's guide wins.
What ships with it
3 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.
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.
- 8d ago Changed · +3 lines d05a91fb9397
- 17d ago Changed · -14 lines 5c9019733c31
- 21d ago Changed · -87 tokens per session 3d942e47cca7
- 1mo ago Changed · -40 tokens per session 155ce2bbe4ff
- 1mo ago Changed 6cc1bc5c8046
- 1mo ago Changed · +5 lines c713e608a3e3
- 1mo ago First seen · 212 lines · 252 tokens per session scan A 3620d59ad5c2
write-for-humans is a skill published in the GitHub repository melodic-software/claude-code-plugins (26 stars, last pushed today), licensed MIT. It adds 125 tokens to every session and 3,483 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
parallel-orchestrator
Manage parallel Claude Code workstreams using git worktrees. Use when: splitting large tasks across multiple workers, coordinating parallel development, monitoring worker progress, integrating completed work, analyzing work item documents (code reviews, issue lists). Triggers: parallel, orchestrator, worktrees…
parallel-worker
Execute focused implementation tasks in a parallel workflow. Use when: working on assigned files in a worktree, making checkpoint commits, signaling dependencies or blockers, completing orchestrator-assigned tasks. Triggers: worker, checkpoint, worktree, assigned scope, commit prefix, parallel task.
optimize-local-search
For NP-hard optimization: TSP, scheduling, assignment problems. Uses greedy construction + local improvement (2-opt, hill climbing).
solve-constraint-puzzle
For constraint satisfaction: Sudoku, scheduling, N-queens, logic puzzles, SAT-like problems, assignment problems. Uses propagate-then-search pattern.
test-with-examples
For example-driven development: test cases as specifications, input/output pairs, documentation through examples.
validate-before-process
For input validation: check format and constraints before processing, fail fast with clear errors, defensive parsing.