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/voytechg/spec-driven-development/update-docs-structurenpx skills add VoytechG/spec-driven-development --skill update-docs-structuregit clone --depth 1 https://github.com/VoytechG/spec-driven-developmentWhat 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 | $0.00029 | $0.00736 |
| Opus 5 | $0.00015 | $0.00368 |
| Sonnet 5 | $0.00006 | $0.00147 |
| Haiku 4.5 | $0.00003 | $0.00074 |
Grade A, and why
update-docs-structure 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update Docs Structure
Migrate existing area docs to the current plugin structure without losing history or loading unnecessary archival detail. This skill is for docs-layout upgrades, not routine feature work.
Workflow
- Read
AREAS.mdat the project root. Identify the area or areas named by the prompt. - Inventory before reading.
- List files under each area's docs root.
- Check sizes with
wc -l. - Scan headings with
rg -n "^#|^##|^###". - Read full files only when the inventory shows they are active docs or need migration.
- Classify docs by purpose.
- Active:
README.md,spec.mdorproduct-spec.md,implementation-status.md, active feature specs, active plans. - Operations:
operations.mdor existing runbooks with commands, env, deploy/import/export, retries, or stop conditions. - Decisions:
decisions/records plus a shortdecisions/README.mdindex. - History:
logs/, shipped plans, old run reviews, verification history, import manifests, and archives.
- Active:
- Propose the target shape before large rewrites. For small updates, proceed directly. For large or ambiguous doc sets, summarize the migration map and ask before moving content.
- Migrate and prune deliberately.
- Keep active docs compact.
- Move old verification/run detail to
logs/. - Convert long chronological decisions into atomic decision records plus a short index when practical.
- Move shipped or superseded plans/specs into
archive/when their active contract has a replacement. - Prune old-format docs such as monolithic
decisions.md, bloated status ledgers, duplicated acceptance files, and obsolete plans after preserving needed history and updating links. - Remove old-path files completely once active references are updated. Do not keep compatibility shims or pointer files unless the user explicitly asks for backwards compatibility.
- Preserve source material; do not delete history unless explicitly requested.
- Use the latest structure.
- Acceptance checks live in the active spec unless a separate checklist is clearly useful.
operations.mdexists only for real runbook needs.implementation-status.mdis a current snapshot: current state, next checkpoint, active plan, deferred work, known gaps, latest verification.- Decision detail lives in
decisions/YYYY-MM-DD-short-title.md; indexes stay short.
- Check references before pruning.
- Use
rgto find links and prose references to files being removed or archived. - Update active-doc reading order, runbook indexes, and in-repo references.
- Report any remaining external-link risk explicitly.
- Use
- Verify.
- Run
git diff --check. - Re-scan the docs root to confirm active docs are small and history is discoverable.
- Report which docs were read, changed, archived, pruned, or intentionally left alone.
- Run
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 · 55 lines · 29 tokens per session scan A 27086eaaa1a2
update-docs-structure is a skill published in the GitHub repository VoytechG/spec-driven-development (4 stars, last pushed 3mo ago), licensed MIT. It adds 29 tokens to every session and 736 once invoked, about $0.0001 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…