documentation-sync

documentation-sync is a skill for Claude Code, Codex from volantlabs/vellis. It costs 57 tokens per session (806 once invoked), scanned A, original, Apache-2.0.

A guide for keeping human-written documentation aligned with the project's canonical SysML models, generated views, code, tools, and workflow rules. Canonical means the source treated as the official definition.

In plain words
What is it for?
Use it after changing models, code, generated views, READMEs, agent instructions, skills, commands, or documented behavior to review and update the affected documentation.
Why use it?
It prevents documentation from becoming outdated or contradicting the model and implementation. It also checks changes across generated files, new files, and public behavior.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/volantlabs/vellis/documentation-sync
Any agent
npx skills add volantlabs/vellis --skill documentation-sync
Clone the repo
git clone --depth 1 https://github.com/volantlabs/vellis

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for documentation-sync

README.md
[![agentmods](https://agentmods.dev/badge/skills/volantlabs/vellis/documentation-sync.svg)](https://agentmods.dev/skills/volantlabs/vellis/documentation-sync)
Your own site
<a href="https://agentmods.dev/skills/volantlabs/vellis/documentation-sync"><img src="https://agentmods.dev/badge/skills/volantlabs/vellis/documentation-sync.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 806 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00057 $0.00806
Opus 5 $0.00028 $0.00403
Sonnet 5 $0.00011 $0.00161
Haiku 4.5 $0.00006 $0.00081

Measured 4d ago against content hash 3a042499dc3f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

documentation-sync 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 4d 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.

.agents/skills/documentation-sync/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentation Sync

Keep each documentation projection useful without creating a second source of component truth.

Source Direction

textual SysML/KPAR -> generated component, application, and manifest views

Hand-authored Markdown may explain rationale, tutorials, operations, evolution, or unresolved questions. It must not independently restate normative action signatures, state, dependencies, or invariants.

Workflow

  1. Inventory canonical model, implementation, generated, documentation, and skill changes from version-control status and diffs. Include untracked files; an ordinary diff omits newly added documentation and can hide an incomplete sync.
  2. Run just model-render for parser-backed inventories, model-derived views, conformance objectives, and manifests.
  3. Review generated component pages for actions, signatures/defaults, typed failures, state access, required constraints, asserted satisfiers, native action calls, invariants, and subject-compatible verification objectives. A fresh but semantically incomplete projection fails sync.
  4. When an accepted source or prior model exists, confirm the projection preserves its public meaning unless an explicit contract change was approved.
  5. Before deleting predecessor documentation, classify its remaining content: contractual facts move to the model; rationale, tutorials, operations, evolution notes, and unresolved questions move to a clearly non-normative home; obsolete statements cite the current model decision that supersedes them. Confirm implementation discoveries are either modeled intentionally or recorded as realization drift.
  6. When package ownership or imports change, update library/application indexes and confirm the generated dependency direction still matches the canonical model.
  7. Update only hand-authored documents whose readers need new context or workflow guidance.
  8. Update AGENTS when repository-wide authoring or realization rules change.
  9. Update reusable skills only for generally applicable workflow improvements; keep product names, project findings, and repository-specific package maps in repository guidance.
  10. Update skill UI metadata when a skill's purpose changes.
  11. Confirm packaged products validate independently and downstream products consume packaged dependencies, then run just skills-check, just model-check, local-link and documentation- guidance checks when available, and the narrowest relevant repository checks.

Read the full file on GitHub · 72 lines

Files

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.

Changes

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.

  1. 4d ago First seen · 72 lines · 57 tokens per session scan A 3a042499dc3f

Subscribe to this mod's changes

documentation-sync is a skill published in the GitHub repository volantlabs/vellis (8 stars, last pushed 10d ago), licensed Apache-2.0. It adds 57 tokens to every session and 806 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.