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 petar-djukic/writing-skills --skill pattern-languagegit clone --depth 1 https://github.com/petar-djukic/writing-skillsWrote 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/petar-djukic/writing-skills/pattern-language)<a href="https://agentmods.dev/skills/petar-djukic/writing-skills/pattern-language"><img src="https://agentmods.dev/badge/skills/petar-djukic/writing-skills/pattern-language/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/petar-djukic/writing-skills/pattern-language"><img src="https://agentmods.dev/badge/skills/petar-djukic/writing-skills/pattern-language.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 | $0.00099 | $0.01489 |
| Opus 5 | $0.00049 | $0.00745 |
| Sonnet 5 | $0.00020 | $0.00298 |
| Haiku 4.5 | $0.00010 | $0.00149 |
Grade A, and why
pattern-language 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 9d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pattern language (mine materials, write the YAML)
This skill turns a repository's materials into a pattern-language.yaml in
the Alexandrian tradition: not a catalogue of tips but a language — each
pattern names a field of forces and the configuration that resolves them, and
the grammar connects each pattern to the ones that create its context and the
ones that complete it.
Where things live
- Format:
references/format-spec.md— the schema (header block, top-level keys, entry keys, grammar semantics, quality bar), distilled from the three existing instances. - Method:
references/mining-guide.md— forces-first extraction, the confidence rubric, disqualifiers, ordering, sizing. - Skeleton:
assets/template.yaml— copy to start a new language; it validates as-is. - Validator:
scripts/validate_language.py <file>— structural checks (keys, unique ids/numbers, grammar resolution, cites, connectivity);--fix-planadds a concrete suggested edit per finding (read-only).
Known instances (study before writing)
| File | Role |
|---|---|
declarative-agents/design-patterns/pattern-language.yaml |
the canonical: 11 build-time patterns, full field set, rich external examples |
agent-failure-modes/aaai-2027/pattern-language.yaml |
extends the canonical (da: prefix); paper scaffolding with paper bindings |
agent-failure-modes/ieee-tse/pattern-language.yaml |
paper scaffolding with paper_sections/experiments; delegates citations via bibliography_note |
The workflow
1. Study the neighbors
Read the known instances (above) and any pattern language already in or near
the target repository. Two things come from this: the format by example, and
the scope boundary — a structure already named in a sibling language is
never restated; it is linked (extends with a prefix, grammar.overlaps, or
examples.kind: sibling). Decide up front what this language covers that no
sibling does, and write that boundary into the header comment.
What ships with it
4 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.
- 9d ago First seen · 143 lines · 99 tokens per session scan A 8765a24ec92e
pattern-language is a skill published in the GitHub repository petar-djukic/writing-skills (4 stars, last pushed 5d ago), licensed MIT. It adds 99 tokens to every session and 1,489 once invoked, about $0.0005 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
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague…
structural-humanizer
Remove the discourse-level (structural) signs of AI writing that survive surface editing: stated lessons and moral-of-the-story closers, tidy single-track arcs, embodied-emotion performance ("chest tightened"), vague allusions instead of named references, unbroken linear structure, and shape convergence across pieces.…
story-import
A tool for turning an existing novel into a structured writing project. It analyzes the book and organizes its characters, settings, plot plans, chapters, and tracking data for later writing.
story-review
A review workflow for finding story problems from several viewpoints, including issues with structure, characters, wording, and fictional world rules. It can use multiple reviewer agents or work alone.
story-deslop
A writing editor for Chinese web novels that detects writing patterns often associated with AI-generated text and makes the prose feel more natural.
story-long-analyze
A long-form fiction analysis workflow for breaking down a novel’s opening chapters, characters, pacing, turning points, relationships, and overall structure.