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 arch3rPro/dsh-skills --skill documentation-placementgit clone --depth 1 https://github.com/arch3rPro/dsh-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/arch3rpro/dsh-skills/documentation-placement)<a href="https://agentmods.dev/skills/arch3rpro/dsh-skills/documentation-placement"><img src="https://agentmods.dev/badge/skills/arch3rpro/dsh-skills/documentation-placement.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 5.1 | $0.00069 | $0.01054 |
| Opus 5 | $0.00034 | $0.00527 |
| Sonnet 5 | $0.00014 | $0.00211 |
| Haiku 4.5 | $0.00007 | $0.00105 |
Grade A, and why
documentation-placement 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Placement
A discipline for arranging documentation so a reader can find a fact exactly once. The core rule is one home per fact: each fact lives in the tier whose job it is, and everywhere else it is a link. This skill tells you where a fact belongs, how deep to go, and how to classify a document. It applies to any repo with documentation.
The defining constraint: the authoring order is locate → set detail → classify → relocate descendant detail → link. You decide where a fact lives before you write it, not after.
The tier taxonomy: one home per fact
Documents form a hierarchy of tiers, each with a job. Place a fact in the tier whose job it is; elsewhere, link there.
| Tier | Job | Does NOT belong there |
|---|---|---|
| Standing orders (top-level agent instructions) | Rules an agent needs in context every session, one to three lines each, linking its home | Stories, worked examples, anything restated from a linked home |
| Architecture map | Ordered map of the system — composition, core pieces, flows, extension points | Type definitions, per-module detail, decision rationale |
| Reference (one page per module/subsystem) | Type definitions, semantics, generated API | Behavior narration |
| Decision records | Active decisions — the why, what was given up, required verification | Migration plans, spec-speak once the decision has shipped |
| How-tos / cookbook | Step-by-step guides with numbered verify steps | Design rationale |
| Package/module README | The per-module consumer contract: config, semantics, limitations, extension points | JSDoc restatement, generated-catalog restatement |
| Generated reference | Exhaustive sources regenerated from source | Hand edits — change the generator instead |
Placement in one sentence: bugs → incident records; rationale → decision records; procedures → how-tos; type definitions → reference pages; package contracts → READMEs; standing orders → the top-level agent instructions.
What ships with it
1 file 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 First seen · 65 lines · 69 tokens per session scan A 2bd1dd20d3ac
documentation-placement is a skill published in the GitHub repository arch3rPro/dsh-skills (4 stars, last pushed 20d ago), licensed MIT. It adds 69 tokens to every session and 1,054 once invoked, about $0.0003 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
dictionary-get-{word}
Returns the definition, phonetics, examples, and synonyms for the given word.
trivia-get-trivia
Returns a random trivia question with multiple-choice answers. Use the optional category and difficulty query parameters to filter the question pool.
dictionary-post-batch
Resolve multiple words in a single request. Returns dictionary entries when found, or error information when a word is not in the dataset.
facts-get-facts
Returns a randomly selected fact, optionally filtered by category.
random-word-get-random
Returns a random word with its definition and part of speech.
cm-notebooklm
Sync high-value dev knowledge (skills, decisions, lessons) into Google NotebookLM for cloud recall, podcasts, and flashcards. Pairs with Dockit/deep-search. Use for NotebookLM, nlm, knowledge base, skill sync, or cross-machine AI memory.