Borrowing it
Nothing to install: this file belongs to luthersystems/elps. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/luthersystems/elps/main/.claude/skills/write-docs/SKILL.mdgit clone --depth 1 https://github.com/luthersystems/elpsWrote 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/luthersystems/elps/write-docs)<a href="https://agentmods.dev/skills/luthersystems/elps/write-docs"><img src="https://agentmods.dev/badge/skills/luthersystems/elps/write-docs/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/luthersystems/elps/write-docs"><img src="https://agentmods.dev/badge/skills/luthersystems/elps/write-docs.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.00798 |
| Opus 5.5 | $0.00000 | $0.00319 |
| Sonnet 5.5 | $0.00000 | $0.00160 |
| Haiku 4.5 | $0.00000 | $0.00080 |
Grade A, and why
write-docs 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/write-docs: House Writing Style
Use this style for all text you write: docs, docstrings, code comments, PR titles and bodies, issue text, release notes and commit messages.
Trigger
Load this skill before you write or edit any text that a person reads.
Rules
Write in the spirit of Simplified Technical English (ASD-STE100).
- Put the answer or the rule first. Put the details after it.
- Keep each sentence to about 20 words or fewer.
- Use active voice and present tense.
- Give each word one meaning. Use the same word for the same thing.
- Write one instruction per sentence.
- Do not use idioms, filler or marketing adjectives. Filler includes "note that", "it's worth noting", "simply" and "basically".
- No mannered prose. Avoid "not X, but Y" framing, colon-then-reveal sentences, scare quotes around invented labels, rhetorical questions and stock phrases such as "worth noting" or "the upshot".
- Do not use em dashes. Use a period, comma, colon or parentheses.
- Do not use emoji. A footer that a repo requires is the only exception.
- Be specific. Give exact names, units, numbers and versions. Cite code
as
path:line. - Write for the reader's next action. Leave out internals the reader does not need.
- Describe what is true now. Do not tell the history of unreleased work (drafts, earlier designs, "this replaced X, which never shipped"). A short "alternatives considered" note is allowed only when it explains a current design choice.
- Never name a customer. Never include customer code or data.
- Link GitHub items as a full markdown link or as
owner/repo#N. Never write a bare#N. - Use a table for comparisons, options and status. Use a list only for parallel items.
Do / Don't
| Don't | Do |
|---|---|
Why does set! fail? It isn't set: it only mutates. |
set! only mutates an existing binding. Use set to create one. |
set! will basically throw an error if the symbol isn't there. |
set! returns an error when the symbol is unbound. |
| Fix #742 | Fix luthersystems/elps#742 |
| The parser was rewritten; it used to be a PEG parser that we dropped. | parser.NewReader returns an rdparser reader. |
| This blazing-fast new builtin makes JSON a breeze! | json:load-bytes parses JSON bytes. JSON objects become sorted-maps. |
| Note that the step budget can be exceeded in some cases. | Exhausting the step budget raises step-budget-exceeded. |
| See the lexer for details. | See parser/lexer/lexer.go:55 (ReadToken). |
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 · 66 lines · 0 tokens per session scan A 015f2180c245
write-docs is a skill published in the GitHub repository luthersystems/elps (36 stars, last pushed today), licensed BSD-3-Clause. It costs nothing until one of its globs matches a file; then it loads 798 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 2026-10-26.
Other skills, from other repositories
migrate-goldmark-extension-v1-to-v2
Migrate goldmark extension from goldmark v1 to v2.
use-modern-go
Use the Modern Go Guidelines CLI whenever writing, modifying, fixing, or refactoring Go code. Apply its version-specific guidance to generated changes.
pi-loop-forensics
Diagnose pi-go agent loops and degenerate turns — "agent loop aborted", runaway thinking with no tool calls, repeated phrases. Discriminates genuine model repetition collapse from a race, a tool-parse failure, or a too-low guard, and A/B replays a seed session across providers.
nightly-session-watch
Nightly sweep of the last 24h of pi-go sessions — anomalous runs, loop aborts, tool error rates, token waste, real prompt-token spend, and whether the observation and palace pipelines are still recording. Triages each finding to the specialist skill that diagnoses it. Use for an unattended daily health check, or on…
tui-render-debug
Diagnose and fix pi-go TUI rendering corruption, especially displaced panels, stale rows, cursor drift, and terminal-specific ANSI incompatibilities.
memory-mine
Mine project files or conversations into the MemPalace memory system. Indexes source code and conversation history as searchable palace drawers with semantic embeddings and room assignment.