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 pvliesdonk/markdown-vault-mcp --skill config-contractgit clone --depth 1 https://github.com/pvliesdonk/markdown-vault-mcpWrote 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/pvliesdonk/markdown-vault-mcp/config-contract)<a href="https://agentmods.dev/skills/pvliesdonk/markdown-vault-mcp/config-contract"><img src="https://agentmods.dev/badge/skills/pvliesdonk/markdown-vault-mcp/config-contract/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/pvliesdonk/markdown-vault-mcp/config-contract"><img src="https://agentmods.dev/badge/skills/pvliesdonk/markdown-vault-mcp/config-contract.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 Anti-Refusal · line 58 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00039 | $0.02333 |
| Opus 5 | $0.00019 | $0.01167 |
| Sonnet 5 | $0.00008 | $0.00467 |
| Haiku 4.5 | $0.00004 | $0.00233 |
Grade A, and why
config-contract 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- config-contract — 86% identical, 4 lines differ
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Config Contract
Config & Customization Contract
Domain configuration composes fastmcp_pvl_core.ServerConfig inside your domain config class (see src/markdown_vault_mcp/config.py). Add domain fields between the CONFIG-FIELDS-START / CONFIG-FIELDS-END sentinels, populate them in from_env between the CONFIG-FROM-ENV-START / CONFIG-FROM-ENV-END sentinels, and enforce their invariants in __post_init__ between the CONFIG-VALIDATE-START / CONFIG-VALIDATE-END sentinels. Validation belongs in __post_init__ rather than from_env because it then also covers a direct ProjectConfig(field=...); env_float / env_int bounds check only the env-sourced value, are inclusive-only, and cannot express cross-field rules. The dataclass is frozen — read fields, don't assign (use object.__setattr__ if a field must be normalised). Never inherit from ServerConfig; always compose.
Env var prefix is MARKDOWN_VAULT_MCP_ — all env reads go through fastmcp_pvl_core.env(_ENV_PREFIX, "SUFFIX", default) so naming stays consistent.
- Domain CLI subcommands go in the
# DOMAIN-COMMANDS-START/-ENDblock incli.py(likeCONFIG-FIELDSinconfig.py). Register them as@app.command()and use function-local imports for domain modules. The block is preserved acrosscopier update.
Config wizard
docs/javascripts/config-wizard/wizard-spec.json drives the guided-setup page. It is generated, produced by scripts/gen_config_surface.py on every copier copy/copier update and re-verified by scripts/gen_config_surface.py --check in CI — never hand-edit it. The runtime (wizard.js, generators.js, wizard-spec-schema.json, the generic tests) is template-owned and re-rendered the same way it always was.
To change what the wizard asks:
- A domain setting your project reads — give its
ProjectConfigfield (between theCONFIG-FIELDS-START/-ENDsentinels inconfig.py) ametadata={"help": ..., "tags": (...)}. The generator's AST scan discovers it from there; no wizard-spec edits needed. - A var the scan cannot see (a deprecated alias no longer read inside
ProjectConfig.from_env, or something read outside it entirely) — declare it inconfig-presentation.domain.ymlinstead. - A path the container needs mounted — add
dockerVolumeto the field'swizardhint:metadata={"help": ..., "tags": (...), "wizard": {"group": "Storage", "dockerVolume": "/data/corpus"}}. When the user supplies a host path, the wizard's Docker and Compose output emits a-v <that answer>:/data/corpusbind mount and sets the var to the container path, instead of an-enaming a host path the container cannot reach. Leaving the field blank emits neither — no mount and no override — so an optional path the user skipped never produces a command pointing at a file that was never mounted. UsedockerPathinstead for a fixed location on the state volume that the server creates itself: it substitutes the path when the var is already present and never adds a mount. The two are mutually exclusive and both must be absolute; the generator rejects a violation by name. - Coverage is enforced, not automatic — the generator fails loudly (
SystemExit, naming the var and its tags) if a collectedVar's tags match no env-file section, rather than silently dropping it from every generated file. Giving a domain field a tag no section lists is a config-presentation bug, and this catches it at generation time instead of shipping an undocumented var. There is, however, no orphan check: a stale or mistaken entry inconfig-presentation.domain.ymlthat nothing actually reads will generate into the wizard and env files anyway. Keep that file's contents matched to real reads yourself.
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.
- 4d ago Changed · +1 lines c6e98e6e8abd
- 7d ago Changed · +7 lines c306fcc00a5e
- 11d ago First seen · 54 lines · 39 tokens per session scan A 41eda5215451
config-contract is a skill published in the GitHub repository pvliesdonk/markdown-vault-mcp (32 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 2,333 once invoked, about $0.0002 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
mnemonic
Search local indexed markdown knowledge bases. Use when the user asks to find notes, dig up a concept from personal docs, cross-reference ideas across wikis, or answer from indexed local files. Triggers on "look up in notes", "search my docs", "what did I write about", "find in my vault", "check my index", "retrieve…
youtube-fetcher
Retrieve YouTube transcripts and subtitles, summarize or analyze what was said, or save an Obsidian-ready Markdown knowledge-base note with captions, creator metadata, chapters, language, and source provenance. Use for a YouTube URL or video ID when the request needs spoken content or an archival note. A bare YouTube…
link-memory
Use after important user-approved decisions, when durable context should be proposed or reviewed, and for explicit Link memory lifecycle work: remember, recall, review, update, archive, restore, forget, or explain local memories through the CLI without requiring MCP.
link-retrieve
Use before answering work that may depend on user memory, project history, source-backed notes, or prior decisions; retrieve compact Link context through the CLI without loading the whole wiki or requiring MCP.
link-ingest
Use when raw files are present, source pages look stale, or a user asks to ingest notes into Link; refresh source-backed wiki pages, propose memories, and validate updates through the CLI without MCP.
reduce
Extract structured knowledge from source material. Comprehensive extraction is the default — every insight that serves the domain gets extracted. For domain-relevant sources, skip rate must be below 10%. Zero extraction from a domain-relevant source is a BUG. Triggers on "/reduce", "/reduce [file]", "extract…