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/shopwarelabs/ai-coding-tools/structuring-documentationnpx skills add shopwareLabs/ai-coding-tools --skill structuring-documentationgit clone --depth 1 https://github.com/shopwareLabs/ai-coding-toolsWhat 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 | $0.00089 | $0.02627 |
| Opus 5 | $0.00044 | $0.01314 |
| Sonnet 5 | $0.00018 | $0.00525 |
| Haiku 4.5 | $0.00009 | $0.00263 |
Grade A, and why
structuring-documentation 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 yesterday.
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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Structuring Documentation
Treat every Markdown file in scope as a documentation surface. Each one holds one subject, one content class, and a bounded amount of reading.
The surfaces in scope are the paths the user names, or the documentation files the current change touches. The script has no default scope and requires explicit paths. When no scope is stated, ask for it rather than assuming one.
Nothing here gates a build. The measurement reports; you act on what it reports.
Budgets are named values: docs.size_goal (default if not otherwise stated: 5000), docs.size_limit (6500), docs.size_ceiling (10000), docs.max_index_rows (20). When earlier context or a user instruction assigns a different value, pass it to the script as --goal, --limit, --ceiling, or --max-index-rows; otherwise run the script on its built-in defaults. When earlier context supplies a subject-ownership table for the project, use it wherever the workflow consults ownership.
Workflow
digraph doc_surfaces {
node [shape=box];
start [shape=doublecircle, label="editing or auditing\na doc surface"];
scope [label="determine the surfaces in scope\n(ask when none is stated)"];
measure [label="run measure.sh size + links"];
subjects [shape=diamond, label="each surface holds one subject,\nowned by its directory\n(references/surface-contract.md)?"];
rehome [label="split the surface, or move the\nsubject to its owning directory"];
over [shape=diamond, label="verdict over\n(above docs.size_ceiling, 10000)?"];
limit [shape=diamond, label="verdict allowance\n(above docs.size_limit, 6500)?"];
crit [shape=diamond, label="is a criterion\ntrue of this file?"];
goal [shape=diamond, label="verdict allowed\n(above docs.size_goal, 5000) with an\nobvious section boundary?"];
split [label="split into docs/ siblings\n(references/splitting.md)"];
nocrit [label="no criterion holds: length alone\nis not one, and neither is\npreferring not to split — split"];
mark [label="mark the allowance or exemption\nunder the title (for size-exempt,\nverify the parsing consumer first)"];
rows [shape=diamond, label="routing rows above\ndocs.max_index_rows (20)?"];
group [label="introduce an\nintermediate grouping"];
links [label="repair citations: convert bare paths,\nfix dead targets and stale anchors,\nrelink restating anchors"];
moved [shape=diamond, label="did this change create a directory\nor move a section body?"];
sweep [label="run the three sweeps, then run\nthem again after the repairs"];
recheck [label="re-run measure.sh"];
resolved [shape=diamond, label="every finding repaired, or\ndismissed with a stated reason?"];
done [shape=doublecircle, label="findings resolved\nor dismissed"];
start -> scope -> measure -> subjects;
subjects -> rehome [label=" no"];
rehome -> over;
subjects -> over [label=" yes"];
over -> split [label=" yes"];
over -> limit [label=" no"];
limit -> crit [label=" yes"];
limit -> goal [label=" no"];
crit -> mark [label=" yes"];
crit -> nocrit [label=" no"];
nocrit -> split;
goal -> split [label=" yes"];
goal -> rows [label=" no"];
split -> rows;
mark -> rows;
rows -> group [label=" yes"];
group -> links;
rows -> links [label=" no"];
links -> moved;
moved -> sweep [label=" yes"];
moved -> recheck [label=" no"];
sweep -> recheck;
recheck -> resolved;
resolved -> over [label=" no"];
resolved -> done [label=" yes"];
}
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.
- yesterday First seen · 182 lines · 89 tokens per session scan A 70cc6c9f979c
structuring-documentation is a skill published in the GitHub repository shopwareLabs/ai-coding-tools (42 stars, last pushed 4d ago), licensed MIT. It adds 89 tokens to every session and 2,627 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
audit-instructions
Audit locally-owned Claude Code instruction surfaces, including CLAUDE.md, .claude/rules, skill bodies, agent definitions, hook instruction text and output styles, for instructions current models no longer need (prior-model workarounds, over-prescriptive scaffolding, stale examples), instructions that misstate Claude…
batch-simplify
Batch-run simplification across changed files, or across an entire repository, grouped by ecosystem and dependency order. Use when: 'batch simplify', 'simplify recent changes', 'simplify everything', 'forgot to run simplify', 'catch up on simplify', 'simplify my branch changes', 'simplify the whole repo', 'simplify…
audit-permission-state
Report the Claude Code permission state actually in effect. Discovers every settings scope (managed policy, user-global, project, local, and the pre-v2.1.211 start-directory copy), merges them into the effective allow/ask/deny set with each rule's source and precedence mechanic named, and classifies which allow rules…
lanes
Start, restart, stop, and check loop lanes as named background Claude Code sessions seeded from canonical prompt files, the scripted replacement for the manual morning refresh (cancel loop, clear, re-paste the canonical prompt) across N lanes on a machine. start/restart first pull the repo and refresh the plugin…
audit-automation-gaps
Audit a repo's Claude Code automation landscape, covering hooks, MCP servers, skills, subagents and scheduled tasks, against the enforcement hierarchy, producing PASS/REJECT/CONDITIONAL verdicts backed by evidence. The default verdict is REJECT because most gaps are already covered by compiler/analyzer/build-time…
audit-prompting-postures
Audit locally-owned instruction components, including skill bodies, agent definitions, hook instruction text, output styles, CLAUDE.md and rules, for MISSING posture guidance the official prompting guide says their purpose needs: delegation criteria/caps in orchestration components, minimal-scope and anti-test-gaming…