Borrowing it
Nothing to install: this file belongs to Heartran/fing-mcp-server. 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/Heartran/fing-mcp-server/main/AGENTS.mdgit clone --depth 1 https://github.com/Heartran/fing-mcp-serverWrote 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/heartran/fing-mcp-server/agents-md)<a href="https://agentmods.dev/instructions/heartran/fing-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/heartran/fing-mcp-server/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/heartran/fing-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/heartran/fing-mcp-server/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 | $0.00575 | $0.00575 |
| Opus 5.5 | $0.00230 | $0.00230 |
| Sonnet 5.5 | $0.00115 | $0.00115 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
fing-mcp-server 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 2mo 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Template developed by Heartran
Commit & Pull Request Guidelines
-
Use short, imperative commit messages (e.g.,
Add dialogue parser,Fix scene load order). Keep changes scoped and commit frequently. -
PRs should include intent, key changes, and testing performed; link related tasks/issues. Add screenshots or short clips for visual changes.
-
Before opening a PR, ensure docs are updated, new commands are documented, and tests (if any) pass locally.
-
All commits should be done using your own git identity
-
Do not work directly on
main, : create a dedicated branch with setup prefix before committing or pushing.- Examples:
windsurf/feature-name,codex/fix-description,gemini/refactor-module
- Examples:
-
Never delete branches (no
--delete-branchon merges) unless explicitly instructed. -
Merge policy (MANDATORY for all agents): unless explicitly specified otherwise by the user, the merge target is ALWAYS
main.- If the target branch is not written clearly in the request, assume
main. - Do not infer a different merge target from recent context/history.
- If the target branch is not written clearly in the request, assume
Identity & Git Hygiene
-
Author/committer identity is managed by the repo owner; do not change git config locally (no
git configcommands). Use the existing configuration as-is. Use $ENV variables for agent-specific commits. -
Never use the Heartran git identity for commits or pushes.
-
Keep commits small and topical; prefer multiple commits over one large drop when touching orthogonal areas.
Git Identity
- Every agent should have his own git identity when committing changes in order to have a more clear and readable history
| Agent | GIT_COMMITTER_NAME / GIT_AUTHOR_NAME | GIT_COMMITTER_EMAIL / GIT_AUTHOR_EMAIL |
|---|---|---|
| Codex | Codex | 199175422+chatgpt-codex-connector[bot]@users.noreply.github.com |
| Gemini | Gemini | 176961590+gemini-code-assist[bot]@users.noreply.github.com |
| Cascade | Cascade | [email protected] |
| GitHub Copilot | Copilot[bot] | 198982749+Copilot[bot]@users.noreply.github.com |
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.
- 2mo ago First seen · 43 lines · 575 tokens per session scan A e5e03fdaf083
fing-mcp-server AGENTS.md is an instructions file published in the GitHub repository Heartran/fing-mcp-server (0 stars, last pushed 7mo ago), licensed MIT. It adds 575 tokens to every session, about $0.0023 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 2026-08-31.
fing-mcp-server AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| fing-mcp-server AGENTS.mdHeartran/fing-mcp-server | Instructions file | 0 | 7mo ago | MIT | A | 575 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |