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/vish288/mcp-coda/agents-mdgit clone --depth 1 https://github.com/vish288/mcp-codaWrote 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/vish288/mcp-coda/agents-md)<a href="https://agentmods.dev/instructions/vish288/mcp-coda/agents-md"><img src="https://agentmods.dev/badge/instructions/vish288/mcp-coda/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 5.1 | $0.01803 | $0.01803 |
| Opus 5 | $0.00901 | $0.00901 |
| Sonnet 5 | $0.00361 | $0.00361 |
| Haiku 4.5 | $0.00180 | $0.00180 |
Grade A, and why
mcp-coda 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 5d 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mcp-coda — Agent Context
MCP server for the Coda v1 API. 54 tools, 12 resources (2 data + 5 rules + 5 guides), and 5 prompts covering docs, pages, tables, rows, formulas, controls, permissions, folders, publishing, automations, and analytics.
Architecture
- Entry point:
src/mcp_coda/__init__.py— click CLI, loads env, runs FastMCP server - Client:
src/mcp_coda/client.py— async httpx client with all Coda API methods - Tools:
src/mcp_coda/servers/— modular tool files (one per domain: docs, pages, tables, rows, etc.) - Helpers:
src/mcp_coda/servers/_helpers.py— shared_get_client,_ok,_err,_check_write - Resources:
src/mcp_coda/servers/resources.py— MCP resources (static knowledge + live data) - Prompts:
src/mcp_coda/servers/prompts.py— MCP prompts (reusable task templates) - Resource files:
src/mcp_coda/resources/— static markdown files for rules and guides - Config:
src/mcp_coda/config.py—CodaConfigdataclass from env vars - Exceptions:
src/mcp_coda/exceptions.py—CodaApiError,CodaNotFoundError, etc. - Tests:
tests/unit/— 260+ tool-level unit tests
RBAC Model
- Server-level:
CODA_READ_ONLY=trueblocks all write tools - MCP annotations:
readOnlyHint,destructiveHint,idempotentHintper tool - Coda token scope: API token permissions enforce doc-level access
Key Patterns
- Tools never raise — all errors return
_err(e)as JSON string - Every tool returns
str(JSON via_ok/_err) - Write tools call
_check_write(ctx)first - List responses include
{items, has_more, next_cursor, total_count} - Rate limit errors include
retry_afterseconds - Async mutations return
requestIdfor polling viacoda_get_mutation_status
MCP Compliance Rules
Tool Annotations (MANDATORY)
Every tool MUST have annotations={} with at minimum readOnlyHint and openWorldHint.
- Read tools:
annotations={"openWorldHint": True, "readOnlyHint": True, "idempotentHint": True} - Non-destructive write tools:
annotations={"openWorldHint": True, "readOnlyHint": False} - Destructive write tools:
annotations={"openWorldHint": True, "destructiveHint": True, "readOnlyHint": False} - Idempotent writes (PUT/update): add
idempotentHint: True
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.
- 5d ago First seen · 152 lines · 1,803 tokens per session scan A eab907f6356c
mcp-coda AGENTS.md is an instructions file published in the GitHub repository vish288/mcp-coda (2 stars, last pushed 14d ago), licensed MIT. It adds 1,803 tokens to every session, about $0.0090 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
ai-dial-core CLAUDE.md
Claude Code instructions for epam/ai-dial-core, covering claude.md, build & run, set credentials via environment variables, build (skip tests) and run all tests.
ai AGENTS.md
AGENTS.md instructions for vercel/ai, covering agents.md, project overview, repository structure, key directories and core package dependencies.
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
InvestSkill GEMINI.md
Gemini CLI instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
technocore-chat AGENTS.md
AGENTS.md instructions for flop-labs/technocore-chat: CI runs exactly these — run them before pushing.
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).