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/gkoreli/backlog-mcp/agents-mdgit clone --depth 1 https://github.com/gkoreli/backlog-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/gkoreli/backlog-mcp/agents-md)<a href="https://agentmods.dev/instructions/gkoreli/backlog-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/gkoreli/backlog-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 | $0.03723 | $0.03723 |
| Opus 5 | $0.01861 | $0.01861 |
| Sonnet 5 | $0.00745 | $0.00745 |
| Haiku 4.5 | $0.00372 | $0.00372 |
Grade A, and why
backlog-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 — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Guidelines for AI Agents Working in backlog-mcp
Testing
Philosophy
Unit tests only. No integration tests.
- Unit tests mock external dependencies (filesystem, network, etc.)
- Tests should be fast, deterministic, and isolated
- If tests touch real filesystem, they're not unit tests
How It Works
All tests use memfs for in-memory filesystem mocking. Zero real file I/O.
vitest.config.tsloadssrc/__tests__/helpers/setup.tsglobally (server package)setup.tsmocksnode:fswith memfs before any test runs- Tests call real production code (e.g.,
storage.add()) - Production code calls
writeFileSync/readFileSync→ intercepted by memfs → stored in RAM - Filesystem resets between test files (not between individual tests)
Test Locations
| Package | Test location | Count |
|---|---|---|
| Server | packages/server/src/__tests__/*.test.ts |
537 |
| Viewer | packages/viewer/**/*.test.ts |
92 |
pnpm test # All workspace tests
pnpm --filter backlog-mcp test # Server only
pnpm --filter @backlog-mcp/viewer test # Viewer only
Rules
DO:
- Write unit tests that use the mocked fs automatically
- Create test data using production APIs (
storage.add(), etc.) - Use
beforeAll/afterAllfor setup/teardown within a test file - Mock external modules explicitly with
vi.mock()when needed - Use
tmpdir()for path strings — only fs operations are mocked
DON'T:
- Don't write custom fs mocks — use the global memfs setup
- Don't use
beforeEachto reset filesystem (breaksbeforeAllpatterns) - Don't rewrite tests to fit mocks — fix the mock instead
Correct Patterns
// Test using production APIs — memfs handles I/O
it('should create a task', () => {
const task = createTask({ id: 'TASK-0001', title: 'Test' });
storage.add(task);
const retrieved = storage.get('TASK-0001');
expect(retrieved?.title).toBe('Test');
});
// Mock paths module when needed
beforeEach(() => {
vi.spyOn(paths, 'backlogDataDir', 'get').mockReturnValue('/test/data');
});
// Mock specific modules for isolation
vi.mock('../storage/backlog.js', () => ({
storage: { list: vi.fn(), get: vi.fn() },
}));
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 · 322 lines · 3,723 tokens per session scan A d3c1ec10313c
backlog-mcp AGENTS.md is an instructions file published in the GitHub repository gkoreli/backlog-mcp (5 stars, last pushed 1mo ago), licensed MIT. It adds 3,723 tokens to every session, about $0.0186 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
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
mistral-mcp CLAUDE.md
Instructions for Swih/mistral-mcp, covering claude.md — mistral-mcp, 1. identité du projet, 2. règles dures (ne pas transgresser), 3. layout & responsabilités and 4. conventions de code.
pfsense-mcp-server AGENTS.md
AGENTS.md instructions for night4me/pfsense-mcp-server, covering pfsense mcp server, architecture and security, development workflow, long-running validation and test parallelism.
trello-mcp AGENTS.md
AGENTS.md instructions for enthouan/trello-mcp, covering agents.md, project summary, hard constraints, runtime and package manager and common commands.
swag-mcp CLAUDE.md
Claude Code instructions for jmagar/swag-mcp, covering swag mcp - claude memory reference, project overview, core architecture, key components and common development commands.