Borrowing it
Nothing to install: this file belongs to basecamp/basecamp-cli. 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/basecamp/basecamp-cli/main/AGENTS.mdgit clone --depth 1 https://github.com/basecamp/basecamp-cliWrote 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/basecamp/basecamp-cli/agents-md)<a href="https://agentmods.dev/instructions/basecamp/basecamp-cli/agents-md"><img src="https://agentmods.dev/badge/instructions/basecamp/basecamp-cli/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/basecamp/basecamp-cli/agents-md"><img src="https://agentmods.dev/badge/instructions/basecamp/basecamp-cli/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 | $0.02491 | $0.02491 |
| Opus 5.5 | $0.00996 | $0.00996 |
| Sonnet 5.5 | $0.00498 | $0.00498 |
| Haiku 4.5 | $0.00249 | $0.00249 |
Grade A, and why
basecamp-cli 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 24d 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Basecamp CLI Development Context
Getting Started
See CONTRIBUTING.md for build setup, testing, and PR workflow.
The standard development loop in this repo: make changes, run bin/ci, fix
what it catches, repeat until green, then push. Treat bin/ci as your
inner-loop companion, not a final hurdle.
Repository Structure
basecamp-cli/
├── cmd/basecamp/ # Main entrypoint
├── internal/
│ ├── appctx/ # Application context
│ ├── auth/ # OAuth authentication
│ ├── cli/ # CLI framework
│ ├── commands/ # Command implementations
│ ├── completion/ # Shell completion
│ ├── config/ # Configuration management
│ ├── dateparse/ # Date parsing
│ ├── hostutil/ # Host utilities
│ ├── models/ # Data models
│ ├── names/ # Name resolution
│ ├── observability/ # Tracing and metrics
│ ├── output/ # Output formatting
│ ├── presenter/ # Output presentation
│ ├── resilience/ # Retry and backoff
│ ├── sdk/ # Basecamp SDK wrapper
│ ├── tui/ # Terminal UI
│ └── version/ # Version info
├── e2e/ # BATS integration tests
├── skills/ # Agent skills
├── hooks/ # Agent lifecycle hooks (both plugin agents)
├── .claude-plugin/ # Claude Code integration
└── .codex-plugin/ # Codex plugin manifest
Coding-agent integrations
Coding-agent integration lives in internal/harness (agent registry, detection, plugin and
skill health checks) and internal/commands/wizard_agents.go (basecamp setup claude|codex|grok|agents). Claude Code and Codex each get a native plugin from the
basecamp/claude-plugins marketplace and have registrations of their own (claude.go,
codex.go). The plugin is basecamp-cli@37signals. During the deprecation window the marketplace keeps
basecamp as an alias with the same source; setup treats basecamp@37signals as stale and
replaces it by key, and the SessionStart hook (routed through agent-hook pre-commit-snapshot
so older CLIs stay silent) tells alias installs once to switch. That is safe only while
basecamp in the marketplace means this plugin: drop the isStalePluginKey /
CodexLegacyPluginKey handling before the marketplace points basecamp at the hosted
connector. Grok Build has no plugin: it reads the shared ~/.agents/skills/basecamp skill
directly, so it is a row of harness.SkillAgent (name, id, home env var, home directory,
binary) in skill_agent.go, and everything in internal/commands that touches a shared-skill
agent — the setup handler, the BASECAMP_SETUP_AGENT values, doctor's remediation — loops over
harness.SkillAgents() rather than naming it. A new shared-skill agent is a new row; the skill
picker's (Global) row, the prose lists in the installers and the docs are the places to update
by hand. setup <id> never fabricates an agent's home directory: a skill-only agent that is not
detected is reported missing, not created.
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.
- 24d ago Changed · +1 lines · +11 tokens per session 660a1e43b167
- 1mo ago Changed · +6 lines · +132 tokens per session 95e196d0db51
- 1mo ago Changed · +25 lines · +410 tokens per session 6f79aafed54f
- 1mo ago Changed · +15 lines · +269 tokens per session 5197d7bf40dd
- 2mo ago First seen · 159 lines · 1,669 tokens per session scan A e75d0d8b9a51
basecamp-cli AGENTS.md is an instructions file published in the GitHub repository basecamp/basecamp-cli (294 stars, last pushed yesterday), licensed MIT. It adds 2,491 tokens to every session, about $0.0100 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.
basecamp-cli AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| basecamp-cli AGENTS.mdbasecamp/basecamp-cli | Instructions file | 294 | yesterday | MIT | A | 2,491 | Claude Code, 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 | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |