Borrowing it
Nothing to install: this file belongs to rse/ase. 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/rse/ase/master/AGENTS.mdgit clone --depth 1 https://github.com/rse/aseWrote 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/rse/ase/agents-md)<a href="https://agentmods.dev/instructions/rse/ase/agents-md"><img src="https://agentmods.dev/badge/instructions/rse/ase/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/rse/ase/agents-md"><img src="https://agentmods.dev/badge/instructions/rse/ase/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 | $0.05300 | $0.05300 |
| Opus 5.5 | $0.02120 | $0.02120 |
| Sonnet 5.5 | $0.01060 | $0.01060 |
| Haiku 4.5 | $0.00530 | $0.00530 |
Grade A, and why
ase 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 today.
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 — 367 lines — stays where its author put it; the contents beside it link to each section on GitHub.
About
Agentic Software Engineering (ASE) is the opinionated companion tooling of Dr. Ralf S. Engelschall for combining Agentic AI Coding with Software Engineering in tools like Anthropic Claude Code CLI. ASE consists of an agent tool plugin (hooks, skills, sub-agents, meta files), a Command-Line Interface (CLI) tool, and a per-project background service bridged into the agent tool as a Model-Context-Protocol (MCP) server.
The primary target agent tool is Anthropic Claude Code CLI; GitHub
Copilot CLI and OpenAI Codex CLI are secondary targets, selected via
ASE_TOOL=copilot resp. ASE_TOOL=codex or the --tool CLI option.
Repository Layout
ASE ships three deliverables from one repository:
plugin/: the agent tool pluginplugin/skills/ase-xxx-xxx/: the 57 skills, each with aSKILL.md(agent instructions) and ahelp.md(Unix-style manual page), plus optional skill-specific files (likease-help-intent/data.md, the concatenation of allhelp.mdfiles, generated at build-time); thehelp.mdfiles document only the user-facing skill surface (purpose, options, arguments, and usage examples), not the internals of the skills (the workflow steps ofSKILL.md, the leveraged sub-agents, meta files, and MCP tools, and their interplay), so consult theSKILL.mdand its referenced files for the latter and never add implementation details to thehelp.mdfilesplugin/agents/: the sub-agent definitions leveraged by the skillsplugin/meta/: the shared meta files, exposed to skills viaase util meta <name>: the constitution, tenets, persona, dialog, control flow, getopt, and skill output conventions (ase-{constitution,tenets,persona,dialog,control,getopt,skill}.md), the common steps shared by groups of skills (ase-common-*.md), and the artifact formats (ase-format-{meta,task,spec}.md), where the specification formatase-format-spec.mdincludes the SpecBook models and formats descriptionase-format-specbook.mdand the standard SpecBook schema configurationase-format-specbook.yaml, both generated at build-time by SpecBook (@rse/specbook)plugin/hooks/: the per-agent-tool hook wiring (hooks.json,hooks-copilot.json,hooks-codex.json)plugin/output-styles/: the output stylease-terseplugin/mods/: the Claude Code function hooks module ("mod"), type-checked against the downloadedclaude-code.d.ts:ase-mods.tsfor the hooking infrastructure (the only module loaded by the engine, registering the hooks, dispatching them into the other modules, and binding the engine services for them),ase-mods-common.tsfor the shared parts (styled characters, Markdown conversion, wrapping, framing, and the geometry of the band above the prompt),ase-mods-grill.tsfor re-rendering the grilling tables of ASE,ase-mods-help-find.tsfor the intent help (a prompt, other than a skill command, suffixed with a blank and!!matched against the help of all skills, with the proposed commands in the band above the prompt, and closed by!!again),ase-mods-help-compose.tsfor the synopsis form (a skill command, bare or with its typed options and arguments, suffixed with!!composed resp. edited through a form of its SYNOPSIS in the band above the prompt, and applied by!!again),ase-mods-help-show.tsfor the manual band (a skill command, bare or with its typed options and arguments, suffixed with a blank and//toggling the entire manual page of the skill in the band above the prompt, while the command is typed on, until the synopsis form opens),ase-mods-help-browse.tsfor the manpage browser (a prompt of just//, or of a free text suffixed with a blank and//, browsing the manual pages of all skills, filtered by a fuzzy search initially of the free text, in the band above the prompt, with RETURN taking over the command of the selected skill), andase-mods-help-hint.tsfor the hint band (a prompt starting with a skill command showing the entire argument hint of the skill, wrapped over multiple lines, in the band above the prompt, instead of the truncated one-line argument hint of Claude Code, which is dropped for the skills)plugin/.claude-plugin/,plugin/.codex-plugin/,plugin/.github/plugin/: the per-agent-tool plugin manifests
tool/: the@rse/aseCLItool/src/ase.ts: the entry point, wiring all top-level commandstool/src/ase-<command>.ts: one module per CLI command resp. command group:setup,config,service,mcp,hook,statusline,task,task-board,agent,artifact,spec,man,util, andutil-{meta,diagram,worktree,mint,metric,compat}tool/src/ase-lib-*.ts: the generic library modules (lib-log,lib-stdio,lib-table,lib-ignore,lib-version,lib-hash,lib-daemon-clifor the start/status/log/stop CLI commands of all background processes (servers, agents, and the agent fleet), andlib-server-cliandlib-server-bindfor the CLI commands and the HTTP binding of the task store and agent relay servers)tool/src/ase-setup-*.ts: the parts ofase setup(setup-commonfor the shared types and sub-process runner,setup-mcpfor the MCP server registry, andsetup-settingsfor the statusline and output style settings)tool/src/ase-config-*.ts: the parts ofase config(config-scopefor the scope chain and directory resolution,config-schemafor the schema, presets, and write policies, andconfig-corefor the layeredConfigclass and the internal session state)tool/src/ase-service-*.ts: the MCP-only tool modules of the service (service-{kv,getopt,markdown,skills,sleep,state,timestamp}) and its AI usage accounting (service-otelfor the OTLP ingress, the usage windows of the task assignments, and their bookings onto the usage attachments of the tasks)tool/src/ase-task-*.ts: the task functionality, wherease-task.tsitself only forwards thease taskCLI andase_task_*MCP tools to the task store selected byproject.task.store.url, through the local or remote task store clients oftask-store-client(seedocs/task-api.md):task-formatfor the textual task format codec and the lifecycle models, andtask-requestfor the codec of the agent requests attached to tasks, like the edit requests of the task boards- the task store:
task-store-server-clifor thease task storeCLI wrapper,task-store-corefor the transport-agnostic REST API functionality,task-store-server-bindfor its HTTP and WebSocket binding,task-store-plugin-apifor the storage plugin contract,task-store-plugin-delegatefor the plugin loader and the locking storage delegate, the built-in storage pluginstask-store-plugin-{ase,github,gitlab,gitea}(file-based resp. GitHub, GitLab, and Gitea Issues), andtask-store-issuesfor the common parts of all issue tracker storage plugins - the task board:
task-boardfor thease task boardCLI command,task-board-{core,graph,flow,filter,stats}for its model (whereflowis the agent graph along the lifecycle model),task-board-tui(split intotask-board-tui-{model,control,view,popup,style}) for the terminal UI, andtask-board-web-serverfor the browser UI, served by the service, with its client inase-task-board-web-client.{html,ts,vue,styl}, a Vue application bundled by Vite, whose root component is split into the modulestask-board-web-client-{model,editor,control}(shared state and service access, task plan editor, and actions and key dispatching) and the componentstask-board-web-client-{lanes,graph,flow,agents,stats,dialog,popup,title}
tool/src/ase-agent-*.ts: the parts ofase agent:agent-runtimefor the runtime base of all agents,agent-runtime-toolfor the headless agent tool invocation and the decoding of its output,agent-runtime-execfor the processes, temporary directories, jobs, and Git operations,agent-runtime-claimfor the run locks and task claims of the crash recovery,agent-runtime-{phase,request}for the runtime bases of the phase resp. request agents, andagent-runtime-enginefor the engine running every agent of a definition (its phase and request agents) and its facades: the built-in agents, the agents of the definition kinds, and theadhocagentagent-definition-apifor the public, self-contained types of the agent definitions and their hooks (exported as the types of the@rse/asepackage),agent-definition-corefor the definition model (options, YAML, TypeScript, JavaScript, and built-in definition loading, discovery of the definition kinds, hooks, validation, and templates), and the directorytool/src/ase-agent-definition-builtin/with the files{rebooter,condenser,implementer,qualifier,integrator,editor,estimator,researcher}.tsfor the declarative definitions of the modes of the built-in agentsagent-processfor thease agent <kind> start|status|log|stopcommands of a single agent, andagent-fleetfor thease agent fleetsupervisor of multiple agents and the agent relay- the agent relay, selected by
project.relay.urland passing the live presence of the agents to the task boards:agent-relay-server-clifor thease agent relayCLI wrapper,agent-relay-corefor the transport-agnostic in-memory presence,agent-relay-server-bindfor its HTTP and WebSocket binding (mountable into the task store server), andagent-relay-clientfor the relay URL resolution, the client, and the presence reporter of the agents
tool/bin/ase: the published shim, loading compiled output fromdst/tool/man/ase{,-xxx{,-yyy}}.md: the Unix manual pages of all CLI commands (one per command and command group, where the pages of a group with third-level commands likease task storecover them), in the remark-man Markdown format, copied at build-time intodst/man/*.md(shown byase man); they document only the user-facing CLI surface (commands, options, arguments, configuration, and files), not the internals oftool/src/(modules, classes, functions, types, and their interplay), so consult the source code for the latter and never add implementation details to the manual pagestool/plugin/andtool/.claude-plugin/: build-time copies ofplugin/and.claude-plugin/-- never edit them, they are regenerated
pages/: the GitHub Pages site (https://ase.tools), an Astro projectpages/src/pages/: the pages of the site (index.astro,author,design,highlights,news,project,setup,usage,workflows,typing-demo, andusecases/[usecase]), all based onpages/src/layouts/BaseLayout.astropages/src/components/*.astro: the page sections (Section-*), modals (Modal-*), widgets (Widget-*), and client-side features (Feature-*)pages/src/data/*.ts: the content data, especiallyskills.ts(the single source of truth for skill grouping and ordering),manpages.ts(the CLI command tree, read at build-time fromtool/man/*.md),news.ts(the release news, read at build-time fromNEWS.md),terminology.ts(the term definitions, imported at build-time from the siblingterminology.md), andcomparison.ts,fit.ts,methods.ts,nav.ts,previews.ts,site.ts,testimonials.ts,usecases.ts, andusps.ts
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.
- today Changed · +11 lines · +175 tokens per session dbe6e29b2ee5
- yesterday Changed · +19 lines · +290 tokens per session d3339893a90b
- 3d ago Changed · +2 lines · +8 tokens per session b35e88adaab0
- 5d ago Changed · +10 lines · +201 tokens per session da72f5fef90d
- 6d ago Changed · +11 lines · +167 tokens per session 2bc2f341c293
- 7d ago Changed · +8 lines · +139 tokens per session 26d0c793dd5b
- 8d ago Changed · +4 tokens per session 679b183353a3
- 9d ago Changed · +4 lines · +66 tokens per session 8a2778b7f02a
- 10d ago Changed · +82 lines · +1,187 tokens per session b7cf6452a709
- 11d ago First seen · 220 lines · 3,063 tokens per session scan A a8bda7ceacef
ase AGENTS.md is an instructions file published in the GitHub repository rse/ase (60 stars, last pushed today), licensed Apache-2.0. It adds 5,300 tokens to every session, about $0.0212 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 2026-08-30.
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.
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).
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.