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/egarcia74/warp-sql-server-mcp/codacygit clone --depth 1 https://github.com/egarcia74/warp-sql-server-mcpWhat 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 | $0.01110 | $0.01110 |
| Opus 5 | $0.00555 | $0.00555 |
| Sonnet 5 | $0.00222 | $0.00222 |
| Haiku 4.5 | $0.00111 | $0.00111 |
Grade A, and why
warp-sql-server-mcp codacy.instructions.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 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.
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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codacy Rules
Configuration for AI behavior when interacting with Codacy's MCP Server
CRITICAL: After ANY successful edit_file or reapply operation
- YOU MUST IMMEDIATELY run the
codacy_cli_analyzetool from Codacy's MCP Server for each file that was edited, with: rootPath: set to the workspace pathfile: set to the path of the edited filetool: leave empty or unset- Compare results with a baseline captured before editing when one is available, and distinguish pre-existing findings from findings introduced by the edit.
- If any issues are found in the new edits, propose and apply fixes for them.
- Limit the fix-and-reanalyze cycle to three attempts per edited file.
- Stop retrying when the findings remain unchanged, or when the retry limit is reached, and report any unresolved findings to the user.
-
NOTE: Failure to follow this rule is considered a critical error.
When you tried to run the codacy_cli_analyze tool and the Codacy CLI is not installed
- Ask the user, "Codacy CLI is not installed. Would you like me to install it now?"
- If the user responds with "yes", run the
codacy_cli_installtool. After installation succeeds, retry the interruptedcodacy_cli_analyzecall with the original arguments, then continue with the original task. - If the user responds with "no", explain that automatic analysis can be disabled in the extension settings.
- Wait for the user to respond before proceeding with any other actions.
After every response
- If you made any file edits in this conversation, verify you ran
codacy_cli_analyzetool from Codacy's MCP Server.
When there are no Codacy MCP Server tools available, or the MCP Server is not reachable
- Suggest the user the following troubleshooting steps:
- Try to reset the MCP on the extension.
- If the user is using VSCode, suggest they review their Copilot > MCP
settings in GitHub, under their organization or personal account. Refer them
to Settings > Copilot > Enable MCP servers in Copilot. Suggested URL
(https://github.com/settings/copilot/features) or
https://github.com/organizations/{organization-name}/settings/copilot/features(This can only be done by their organization admins or owners.) - If none of the above steps work, suggest the user contact Codacy support.
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 First seen · 98 lines · 1,110 tokens per session scan A 02a01a9c3497
warp-sql-server-mcp codacy.instructions.md is an instructions file published in the GitHub repository egarcia74/warp-sql-server-mcp (5 stars, last pushed 2d ago), licensed MIT. It adds 1,110 tokens to every session, about $0.0056 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
world-intel-mcp CLAUDE.md
Instructions for marc-shade/world-intel-mcp, covering claude.md, what this is, commands, install and run mcp server (stdio mode).
autotask-mcp AGENTS.md
AGENTS.md instructions for WYRE-AI/autotask-mcp, covering task master ai - agent integration guide, essential commands, core workflow commands, project setup and daily development workflow.
pfsense-mcp-server AGENTS.md
Instructions for night4me/pfsense-mcp-server, covering pfsense mcp server, architecture and security, development workflow, long-running validation and test parallelism.
clawstash CLAUDE.md
Claude Code instructions for fo0/clawstash, covering claude.md -- project guide, session start -- read order, workflow triggers, output languages and performance / modes.
sui-mcp CLAUDE.md
Claude Code instructions for 0xfreak0/sui-mcp, covering sui-mcp, stack, architecture, which transport to use and archive fallback.
datadog-mcp CLAUDE.md
Instructions for dreamiurg/datadog-mcp, covering agent instructions, project, stack, commands and releases.