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/michaelcereda/stampo/agents-mdgit clone --depth 1 https://github.com/MichaelCereda/stampoWhat 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 | $0.00813 | $0.00813 |
| Opus 5 | $0.00407 | $0.00407 |
| Sonnet 5 | $0.00163 | $0.00163 |
| Haiku 4.5 | $0.00081 | $0.00081 |
Grade A, and why
stampo AGENTS.md scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
http_tool.rs -- curl/wget detection, command generation, remote fetching How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stampo Agent Instructions
Stampo generates CLIs from YAML configs and OpenAPI specs. See README.md for features and docs/ for full documentation.
Build & Test
Requires Rust toolchain via mise:
eval "$(mise activate zsh)" && cargo build
eval "$(mise activate zsh)" && cargo test
Project Structure
src/
main.rs -- Entry point, mode dispatch (~230 lines)
init.rs -- Init flow, default config creation, references, base-dir resolution
refresh.rs -- Refresh and update-check logic
shell.rs -- Shell detection, alias install, completion hooks
cli.rs -- CLI construction (clap builder API), command execution
config.rs -- Config loading, validation, placeholder/env-var replacement
models.rs -- YAML data structures (Configuration, Command, Flag, CmdType)
cache.rs -- Trusted config storage (~/.stampo/aliases/), SHA-256 hashing
style.rs -- Color output (ANSI, NO_COLOR, --color flag)
errors.rs -- Error types
openapi/
mod.rs -- Public API: process_openapi_source()
parser.rs -- OpenAPI 3.0 spec parsing via openapiv3
transform.rs -- Spec-to-Configuration transformation, path hierarchy, flag generation
http_tool.rs -- curl/wget detection, command generation, remote fetching
tests/
integration.rs -- End-to-end CLI tests (init, completions, OpenAPI, live shell tests)
fixtures/ -- Test YAML configs and OpenAPI specs
docs/
getting-started.md -- Step-by-step setup guide
configuration-reference.md -- Full YAML schema reference
openapi-guide.md -- OpenAPI usage guide
setup-guide.md -- Installation and setup
Architecture
- Dynamic CLI from YAML -- commands are loaded at runtime, must use clap builder API (not derive)
- Two modes: installer (
stampo init) and alias (stampo --alias-mode <name>) - OpenAPI support: specs transformed to Configuration structs at init time, commands use curl/wget
- Trust model: configs cached with SHA-256 in
~/.stampo/aliases/<name>/ - Zero network footprint: no HTTP client in the binary, curl/wget for external tools only
- Placeholder syntax:
${{flag_name}}and${{env.VAR_NAME}} - Shell support: bash, zsh, fish, powershell (functions + tab completion)
- Output: stdout for command output only, stderr for all stampo messages
- POSIX-safe: ASCII-only output, no emojis
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.
- 2d ago First seen · 75 lines · 813 tokens per session scan A d8a9ce3b98c3
stampo AGENTS.md is an instructions file published in the GitHub repository MichaelCereda/stampo (5 stars, last pushed 7d ago), licensed MIT. It adds 813 tokens to every session, about $0.0041 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
cli-printing-press AGENTS.md
AGENTS.md instructions for mvanhorn/cli-printing-press, covering cli printing press - development conventions, machine vs printed cli, anti-reimplementation, agent-native surface and default: expose; skip rules are exceptions.
lathe CLAUDE.md
Instructions for lathe-cli/lathe, covering claude.md, project intent, product positioning, source of truth and project structure.
climate AGENTS.md
Instructions for disk0Dancer/climate, covering agents contribution workflow, required sequence for any feature, quality rules and feature checklist template.
climate CLAUDE.md
Instructions for disk0Dancer/climate, covering climate — claude code instructions, definition of done (non-negotiable), hermetic tests and debugging red ci.
cli-printing-press CLAUDE.md
Claude Code instructions for mvanhorn/cli-printing-press, a project described as: Every API has a secret identity. This finds it, absorbs every feature from every competing tool, then builds the GOAT CLI — designed for AI agents first, with SQLite sync, offline search, and compound insight commands.
lathe AGENTS.md
Instructions for lathe-cli/lathe, a project described as: Agentic-friendly CLI generator for APIs: turn Swagger, OpenAPI, and google.api.http protos into single-binary CLIs with catalogs and generated Skills.