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 instructions/tadmstr/vikunja-mcp/agents-mdgit clone --depth 1 https://github.com/TadMSTR/vikunja-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/instructions/tadmstr/vikunja-mcp/agents-md)<a href="https://agentmods.dev/instructions/tadmstr/vikunja-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/tadmstr/vikunja-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.02911 | $0.02911 |
| Opus 5 | $0.01456 | $0.01456 |
| Sonnet 5 | $0.00582 | $0.00582 |
| Haiku 4.5 | $0.00291 | $0.00291 |
Grade A, and why
vikunja-mcp AGENTS.md 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.
How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — vikunja-mcp
Operating contract for Claude sessions working in this repo.
What this server does
Exposes the Vikunja REST API (/api/v2) as MCP tools for projects, tasks, labels,
comments, saved filters, and webhooks. It is a thin, stateless translator — no business
logic, no caching, no persistence.
Minimum Vikunja is 2.4.0, the release that shipped /api/v2. The version is applied in
client._api_base(), not configured — dual-version support was considered and rejected.
Module boundaries
| Module | Responsibility | Must NOT |
|---|---|---|
config.py |
Env-var settings (upstream URL, transport binding) | Hold any Vikunja token |
auth.py |
Extract the caller's bearer token from the incoming request | Fall back to any ambient/default credential |
client.py |
One pooled httpx client; per-request auth; error mapping; the pagination envelope | Store a token on the client instance |
server.py |
Tool definitions + verb/path mapping to Vikunja | Contain HTTP or credential logic inline |
exceptions.py |
Typed error hierarchy | — |
hooks.py |
Pre/post extension-hook registry, keyed on tool name | Swallow handler exceptions — hooks are not fire-and-forget |
telemetry.py |
Optional OTLP spans/metrics, InfluxDB3, NATS — inert unless env-configured | Become a hard import dependency; a missing extra must degrade, not crash |
contrib/ |
Opt-in add-ons a deployment may register (e.g. audit_log) |
Be imported unconditionally — the one exception is audit_log, gated behind VIKUNJA_AUDIT_LOG=1 in register_builtin_hooks (vikunja#342, id 361); everything else in contrib/ still needs its own explicit registration |
Invariants (do not break)
- No stored credentials. This process never reads a Vikunja token from Vault, env, or
disk. The token arrives per request in the
Authorizationheader and is forwarded verbatim. This is the whole security model — seeSECURITY.md. - Fail closed. A missing or empty
Authorizationheader raisesAuthError; it is never treated as anonymous or defaulted. authorizationmust be explicitly opted intoget_http_headers(include={...})— the library strips it by default.tests/test_auth.py::test_authorization_header_is_explicitly_requestedguards this; do not remove it.- POST creates, PUT replaces, PATCH merges on v2. Keep
*_createon POST and*_updateon PUT.tests/test_server.pypins every mapping andscripts/verify-routes.pychecks it against the live router.
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 First seen · 158 lines · 2,911 tokens per session scan A 9ceee6c5586d
vikunja-mcp AGENTS.md is an instructions file published in the GitHub repository TadMSTR/vikunja-mcp (3 stars, last pushed 2d ago), licensed MIT. It adds 2,911 tokens to every session, about $0.0146 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 instructions, from other repositories
wanaku CLAUDE.md
Claude Code instructions for wanaku-ai/wanaku, covering wanaku, core guidelines, quick start, build info and architecture.
MediaWiki-MCP-Server AGENTS.md
AGENTS.md instructions for ProfessionalWiki/MediaWiki-MCP-Server, covering agents.md, repo layout, imports, commands and tool conventions.
blz AGENTS.md
Instructions for outfitter-dev/blz, covering blz repository instructions for ai agents, important, working memory, use blz and 🚀 quick start for agents.
opencontext CLAUDE.md
Claude Code instructions for slxca/opencontext, covering critical memory system: opencontext protocol, 1. mandatory pre-flight: inspect context, 2. post-implementation: persist changes and 3. execution rules.
moo-tasks AGENTS.md
Instructions for dizlexic/moo-tasks, covering agents.md, 1. what is the moo tasks board?, 2. connecting your agent, 3. available mcp tools and 4. recommended workflow for agents.
htmldrop AGENTS.md
Instructions for vin-spiegel/htmldrop, covering htmldrop — mcp server for publishing html, service endpoints, connect as an mcp client, available tool and publishhtml.