Borrowing it
Nothing to install: this file belongs to volantlabs/vellis. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/volantlabs/vellis/main/.agents/skills/documentation-sync/SKILL.mdgit clone --depth 1 https://github.com/volantlabs/vellisWrote 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/volantlabs/vellis/documentation-sync)<a href="https://agentmods.dev/skills/volantlabs/vellis/documentation-sync"><img src="https://agentmods.dev/badge/skills/volantlabs/vellis/documentation-sync/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/volantlabs/vellis/documentation-sync"><img src="https://agentmods.dev/badge/skills/volantlabs/vellis/documentation-sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 43 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00057 | $0.00806 |
| Opus 5.5 | $0.00023 | $0.00322 |
| Sonnet 5.5 | $0.00011 | $0.00161 |
| Haiku 4.5 | $0.00006 | $0.00081 |
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 2mo 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 — 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
- 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.
- Run
just model-renderfor parser-backed inventories, model-derived views, conformance objectives, and manifests. - 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.
- When an accepted source or prior model exists, confirm the projection preserves its public meaning unless an explicit contract change was approved.
- 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.
- When package ownership or imports change, update library/application indexes and confirm the generated dependency direction still matches the canonical model.
- Update only hand-authored documents whose readers need new context or workflow guidance.
- Update AGENTS when repository-wide authoring or realization rules change.
- Update reusable skills only for generally applicable workflow improvements; keep product names, project findings, and repository-specific package maps in repository guidance.
- Update skill UI metadata when a skill's purpose changes.
- 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.
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.
- 2mo ago First seen · 72 lines · 57 tokens per session scan A 3a042499dc3f
documentation-sync is a skill published in the GitHub repository volantlabs/vellis (9 stars, last pushed 4d ago), licensed Apache-2.0. It adds 57 tokens to every session and 806 once invoked, about $0.0002 per session on Opus 5.5. 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
dkg-importer
Bulk-import a large RDF graph (code graph, corpus, GitHub history, etc.) into a DKG node's working memory. Use this skill when you need to push more than a few thousand triples in a single import — it codifies the chunking budgets, the assertion-loop shape, the resumability manifest, and the canonical URI rules so…
ori-memory
Persistent agent memory with learning retrieval. Knowledge graph on markdown files — capture insights, decisions, research, and learnings during work, then retrieve them weeks or months later. Use when knowledge is too valuable to lose but too much to inject into every prompt.
dkg-node
The DKG V10 Node is your primary memory system. This skill teaches you to operate your node's three-layer verifiable memory — write and retrieve private drafts in Working Memory, share with peers in Shared Working Memory, and publish permanently to Verifiable Memory on-chain.
example-skill
Example module showing the format. Use when: testing /enable-modules, learning to author a module.
graph-ask
Ask any natural language question about the memory graph. You generate Cypher directly and execute it. Use when the user has a complex or ad-hoc question that the standard graph tools don't cover.
capture-knowledge
A guide for saving useful, reusable knowledge from conversations and documents into a structured personal knowledge base. It separates original source material from concise pages about individual concepts.