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/sairam0424/ag-bash/agents-mdgit clone --depth 1 https://github.com/sairam0424/ag-bashWrote 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/sairam0424/ag-bash/agents-md)<a href="https://agentmods.dev/instructions/sairam0424/ag-bash/agents-md"><img src="https://agentmods.dev/badge/instructions/sairam0424/ag-bash/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 | $0.02259 | $0.02259 |
| Opus 5 | $0.01130 | $0.01130 |
| Sonnet 5 | $0.00452 | $0.00452 |
| Haiku 4.5 | $0.00226 | $0.00226 |
Grade A, and why
ag-bash 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 4d 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Architecture
Ag-Bash is a pnpm monorepo (v6.0.0) with three packages: @ag-bash/bash (core shell engine), @ag-bash/mcp-server (MCP protocol server), and @ag-bash/agent-bridge (terminal UI bridge).
v6.0.0 export paths (in addition to the main @ag-bash/bash entry):
@ag-bash/bash/agent-runtime— RunLoop for autonomous agent execution@ag-bash/bash/testing— Test utilities (createTestBash,assertSuccess,assertFails)
Core pipeline: Input Script → ExecutionPipeline [Normalize → Parse (src/parser/lexer/) → Transform → Sandbox → Interpret (src/interpreter/) → Persist] → BashExecResult
New in v6.0.0:
src/parser/lexer/— Tokenization layer in parser subdirectorysrc/agentic/toolbox/— Builtin command implementations (BashToolbox) in agentic subdirectorysrc/execution/— ExecutionPipeline (sole engine), stages, and DestructiveStagesrc/streaming/— StreamingExecutor and true incremental outputbash.fork()/bash.speculate()— Copy-on-write branching for agentic speculationbash.execStream()— AsyncGenerator-based streaming output
Key architectural patterns:
- ServiceContainer DI (v3.0 breaking change, v6.0.0 registry pattern): All services are per-
Bashinstance viacreateDefaultServices(). No singletons exceptDefenseInDepthBox(security necessity). Multiple Bash instances share zero mutable state. The container uses lazy initialization with a registry pattern (2 eager:astCache+sharedBus). - BashHost interface: Typed command dispatch for all builtins via the
BashHostinterface. - AsyncDisposable:
BashimplementsAsyncDisposablefor deterministic resource cleanup. - ServiceContainer registry in
src/services/: ASTCache, SharedStateBus, AgentManager, SessionManager, TaskManager, TeamManager, WorktreeManager, AgentMemory (now persistent across sessions), McpClient, Orchestrator, LSPManager, GitTracker, CronScheduler, PermissionManager. - Pluggable filesystems: InMemoryFs, OverlayFs (CoW), ReadWriteFs, MountableFs — all gated by
resolveAndValidate(). - WASM runtimes: CPython and QuickJS sandboxed via SharedStateBus bridge (opt-in).
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.
- 4d ago First seen · 151 lines · 2,259 tokens per session scan A e435a03259be
ag-bash AGENTS.md is an instructions file published in the GitHub repository sairam0424/ag-bash (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,259 tokens to every session, about $0.0113 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 2026-08-30.
Other instructions, from other repositories
signoz-mcp-server CLAUDE.md
Instructions for SigNoz/signoz-mcp-server, covering claude.md — development conventions, feature planning convention, rules, git & pr and code style.
remnote-mcp-server AGENTS.md
Instructions for robert7/remnote-mcp-server, covering agents.md, repo role, companion repos (sibling dirs), contract map (current) and external mcp tool surface (17).
lain copilot-instructions.md
Copilot instructions for spuentesp/lain, covering lain — codebase intelligence, when to use lain, the most useful tools, workflows and caveats.
mcp-read-only-grafana CLAUDE.md
Instructions for lukleh/mcp-read-only-grafana, covering claude.md, project overview, runtime config location, development commands and install dependencies.
sentry-mcp AGENTS.md
AGENTS.md instructions for VitalyOstanin/sentry-mcp, covering repository guidelines, contributor notes, planning workflow, documentation guidelines and language policy.
mcp-read-only-grafana AGENTS.md
Instructions for lukleh/mcp-read-only-grafana, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.