Borrowing it
Nothing to install: this file belongs to ufna/vikunja-mcp. 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/ufna/vikunja-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/ufna/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/ufna/vikunja-mcp/claude-md)<a href="https://agentmods.dev/instructions/ufna/vikunja-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ufna/vikunja-mcp/claude-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 5.1 | $0.10544 | $0.10544 |
| Opus 5 | $0.05272 | $0.05272 |
| Sonnet 5 | $0.02109 | $0.02109 |
| Haiku 4.5 | $0.01054 | $0.01054 |
Grade B, and why
vikunja-mcp CLAUDE.md scanned grade B with 2 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 2d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
dependency-free POSIX-`sh` script registered in `~/.claude/settings.json` that, ONLY Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
until curl -sf http://localhost:3456/api/v1/info >/dev/null; do sleep 1; done How it starts
The opening of the file, as written. The whole thing — 522 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code when working in this repository.
How this file is organised — read this first. What lives here are RULES: short,
imperative, binding. The evidence under them — measurements, constructed stands,
refuted wordings, the per-card post-mortems — lives in docs/dossier/*.md, one file
per subsystem, linked at the end of each section and from the module's own docstring.
Two consequences, both binding:
- Changing a module? Read its dossier first. The rule here is short precisely because the proof is there. This repo has repeatedly "fixed" a guard by reasoning instead of measuring, several rounds running; if a rule looks redundant or simplifiable, the answer is almost certainly in the dossier. The reviewer checks that it was read.
- A new card's post-mortem goes to the card and to the dossier, NOT here. This
file enters EVERY session's context — the orchestrator's, every per-task agent's
and every reviewer's; at
wip_limit = 3that is ~7 contexts per round. Edit here only when the RULE itself changed. The size of both rulebooks is pinned bytests/unit/test_rulebook_size.py, which is a ratchet: when it shrinks, lower the ceiling in the same commit.
What This Is
Workflow-level MCP server for a self-hosted Vikunja tracker — NOT a CRUD wrapper. The pipeline and its gates ARE the product:
Backlog → Queue → Design → Build → Review → [human] → Done
↕ ↕
Your Call (+ independent review of EVERY task in Review)
14 agent tools (next_task, claim, get_task, comment, advance,
call_human, return_task, decompose, file_task, review_task,
attach_file, download_attachment, handoff, transfer_task); agents can
never move a task to Done —
that transition is human-only by design. Gates are guardrails for agents; the
real security boundary is the scoped API token.
Commands
uv sync # env (Python 3.11+, uv)
uv run pytest tests/unit -q # 500+ unit tests (FakeAPI, MockTransport)
uv run ruff check . # lint — wrap at 100, RED above 110 (see below)
uv run vikunja-mcp --version # smoke
uv run vikunja-mcp claimable # one JSON line: is there claimable work for this
# token? (hgdev-acp hub's pre-launch idle check)
# integration — real Vikunja 2.3.0 in docker (skipped without VIKUNJA_TEST_URL):
docker run -d --name vikunja-test -p 3456:3456 \
-e VIKUNJA_DATABASE_TYPE=sqlite -e VIKUNJA_DATABASE_PATH=/tmp/vikunja.db \
-e VIKUNJA_FILES_BASEPATH=/tmp/files -e VIKUNJA_SERVICE_JWTSECRET=integration-test-secret \
-e VIKUNJA_SERVICE_PUBLICURL=http://localhost:3456/ -e VIKUNJA_SERVICE_ENABLEREGISTRATION=true \
vikunja/vikunja:2.3.0
until curl -sf http://localhost:3456/api/v1/info >/dev/null; do sleep 1; done
VIKUNJA_TEST_URL=http://localhost:3456 uv run pytest tests/integration -q
docker rm -f vikunja-test
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.
- 2d ago Changed · +7 lines · +177 tokens per session e9aea4409cd6
- 3d ago Changed · +12 lines · +257 tokens per session d8c0ce87a85b
- 7d ago First seen · 503 lines · 10,110 tokens per session scan B d15cbaf3f9aa
vikunja-mcp CLAUDE.md is an instructions file published in the GitHub repository ufna/vikunja-mcp (3 stars, last pushed 2d ago), licensed MIT. It adds 10,544 tokens to every session, about $0.0527 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.