Borrowing it
Nothing to install: this file belongs to yaniv-golan/mcp-bash-framework. 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/yaniv-golan/mcp-bash-framework/main/AGENTS.mdgit clone --depth 1 https://github.com/yaniv-golan/mcp-bash-frameworkWrote 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/yaniv-golan/mcp-bash-framework/agents-md)<a href="https://agentmods.dev/instructions/yaniv-golan/mcp-bash-framework/agents-md"><img src="https://agentmods.dev/badge/instructions/yaniv-golan/mcp-bash-framework/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/yaniv-golan/mcp-bash-framework/agents-md"><img src="https://agentmods.dev/badge/instructions/yaniv-golan/mcp-bash-framework/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 | $0.01581 | $0.01581 |
| Opus 5.5 | $0.00632 | $0.00632 |
| Sonnet 5.5 | $0.00316 | $0.00316 |
| Haiku 4.5 | $0.00158 | $0.00158 |
Grade A, and why
mcp-bash-framework 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 3d 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.
AGENTS.md
Guidance for anyone (human or AI agent) changing mcp-bash-framework. It covers what isn't obvious from the code. Setup, test commands and the release checklist live in CONTRIBUTING.md and TESTING.md; read those first.
Repository map
| Path | What it is |
|---|---|
bin/mcp-bash |
CLI entry point and server launcher |
lib/ |
Runtime: read loop and workers (core.sh), JSON (json.sh), env isolation (tools.sh, meta_env.sh), resources and template matching (resources.sh, resource_match.sh), verified file reads (file_read.sh), HTTPS/git address policy (policy.sh), CLI subcommands (lib/cli/) |
handlers/ |
One file per MCP method family (lifecycle.sh, resources.sh, completion.sh, ...) |
providers/ |
Built-in resource providers (file, https, git, ui) |
sdk/ |
Helpers sourced by tool scripts (tool-sdk.sh) |
scaffold/ |
Templates for mcp-bash new / scaffold |
examples/ |
Numbered examples 00–15, advanced/, and 99-test-fixtures |
test/ |
lint.sh, smoke.sh, run-all.sh, unit/ (bats), integration/, examples/, stress/, compatibility/, conformance/, benchmark/, shared helpers in common/ |
hooks/pre-commit |
Git pre-commit hook |
tools/ |
Go module pinning developer tools |
scripts/ |
render-readme.sh, bump-version.sh, ... |
docs/ |
User docs; docs/ENV_REFERENCE.md lists every variable |
README.md is generated: edit README.md.in, then run bash scripts/render-readme.sh.
Portability traps
The server must run on macOS /bin/bash 3.2 (what GUI hosts such as Claude Desktop
launch) and on bash 4+/5, with jq, gojq or jq 1.6, on macOS, Linux and Git Bash.
bash 3.2:
"${arr[@]}"on an empty array is an "unbound variable" error underset -u. Use${arr[@]+"${arr[@]}"}.printf '%d' "'c"is negative for bytes ≥ 0x80. Mask with$(( code & 255 )).read -treturns 1 on timeout (bash 4+: > 128), so status 1 is not EOF on 3.2.- With
set -eand an EXIT trap, a fatal error can exit 0. Don't trust exit status alone in tests; check for the expected output too. - No
BASH_XTRACEFD, no${var,,}, no associative arrays, nomapfile. - After a failed write to stdout (EPIPE), unwritten bytes stay in bash's buffer and leak
into later
$(...)output.
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.
- 3d ago Changed · +7 lines · +151 tokens per session 653bc5e9bcfd
- 5d ago First seen · 91 lines · 1,430 tokens per session scan A 0a5e6aa9f9ff
mcp-bash-framework AGENTS.md is an instructions file published in the GitHub repository yaniv-golan/mcp-bash-framework (11 stars, last pushed today), licensed MIT. It adds 1,581 tokens to every session, about $0.0063 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 2026-10-11.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).