Borrowing it
Nothing to install: this file belongs to simonether/kwork-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/simonether/kwork-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/simonether/kwork-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/simonether/kwork-mcp/agents-md)<a href="https://agentmods.dev/instructions/simonether/kwork-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/simonether/kwork-mcp/agents-md/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/instructions/simonether/kwork-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/simonether/kwork-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.02198 | $0.02198 |
| Opus 5.5 | $0.00879 | $0.00879 |
| Sonnet 5.5 | $0.00440 | $0.00440 |
| Haiku 4.5 | $0.00220 | $0.00220 |
Grade A, and why
kwork-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 1mo 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kwork-mcp
Stdio MCP gateway for the Kwork freelance marketplace: 22 tools (18 typed reads + a
durable prepare → commit → reconcile write protocol) on FastMCP 4 / MCP SDK 2 over the pinned
kwork==0.2.0 client. Python 3.12–3.14, managed with uv.
Commands
uv run ruff check .— lintuv run ruff format --check .— format checkuv run mypy— strict type checkuv run python -m pytest tests/ -q— testsuv run python -m pytest tests/ -q --cov=kwork_mcp --cov-report=term-missing— tests + coverage (gate: 92% branch)uv run kwork-mcp— start the server (stdio); needs a bootstrapped accountuv run kwork-mcp login— human TTY CLI: account auth; alsostatus,logout,pending-writes,resolve-write(kwork-mcp-bootstrapis the old alias)
Project map
src/kwork_mcp/
__init__.py main(): bare command = stdio server (rejects secret env, no banner); args → terminal CLI
bootstrap.py terminal CLI: login (TTY auth → store, prints client commands), status, logout, write resolution
config.py KworkConfig (pydantic-settings, KWORK_ prefix), bound-account selection, proxy validation
server.py create_server(): FastMCP app, lifespan, SERVER_INSTRUCTIONS, unknown-tool guard
session.py KworkSessionManager: lazy auth, account identity checks, call_read / call_write_step
coordination.py CoordinationStore: shared SQLite — rate limits, circuits, cursors, write ledger, writer lock
contracts.py pinned pykwork signatures and generic route params (enforce_route_params)
security.py SecureTokenStore, sanitize_external / redact_text, log redaction
errors.py GatewayError taxonomy, classify_upstream_error
models.py ResultEnvelope, records, write requests, WriteState
middleware.py strict, sanitized tool-input validation
upstream.py GatewayKworkClient (keeps success:false payloads), secure web client
gateway/ layered gateway, each module builds on the previous one:
parsing.py envelope/paging/scalar helpers
base.py shared state
reads.py typed read operations
lookups.py exhaustive scans for preflight and read-back
offer_flow.py submit_offer web flow (form → FAQ → draft → template check → create)
actions.py one ActionHandler per WriteAction: preflight / execute / read_back
writes.py durable prepare / commit / status / reconcile protocol
tools/ read_tools.py, write_tools.py, common.py (envelope helpers, annotations)
tests/ pytest suite; test_live_contracts.py holds anonymized live response shapes
docs/ architecture, configuration, security, migration and release notes (Russian)
site/ GitHub Pages landing page (Russian), deployed by .github/workflows/pages.yml;
static, no build: index.html, style.css, app.js, theme.js, self-hosted fonts/;
og.png is rendered from assets/og.html; the pinned version is checked by tests
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.
- 1mo ago Changed · +13 lines · +283 tokens per session 9cd9d855e982
- 1mo ago Changed · +17 lines · +351 tokens per session df5f8e7fc955
- 1mo ago Changed · +4 tokens per session e15e9cb77c86
- 1mo ago First seen · 107 lines · 1,560 tokens per session scan A 5b58cf903f1b
kwork-mcp AGENTS.md is an instructions file published in the GitHub repository simonether/kwork-mcp (6 stars, last pushed 4d ago), licensed MIT. It adds 2,198 tokens to every session, about $0.0088 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 2026-09-26.
kwork-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| kwork-mcp AGENTS.mdsimonether/kwork-mcp | Instructions file | 6 | 4d ago | MIT | A | 2,198 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |