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/aarongoldsmith/mcp-printable/claude-mdgit clone --depth 1 https://github.com/AaronGoldsmith/mcp-printableWrote 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/aarongoldsmith/mcp-printable/claude-md)<a href="https://agentmods.dev/instructions/aarongoldsmith/mcp-printable/claude-md"><img src="https://agentmods.dev/badge/instructions/aarongoldsmith/mcp-printable/claude-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 5.1 | $0.02099 | $0.02099 |
| Opus 5 | $0.01050 | $0.01050 |
| Sonnet 5 | $0.00420 | $0.00420 |
| Haiku 4.5 | $0.00210 | $0.00210 |
Grade A, and why
mcp-printable CLAUDE.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 5d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project notes for Claude
Operational context for any Claude Code session in this repo. The README is for users; AGENTS.md is for cross-agent guidance about using the MCP. This file is for Claude when working on the project itself — branch protection, release flow, naming gotchas.
Repo & PyPI
- Repo: https://github.com/AaronGoldsmith/mcp-printable (public)
- PyPI: https://pypi.org/project/mcp-printable/
- Default branch:
main(protected — see below) - Maintainer: AaronGoldsmith (solo)
Branch protection on main is ON
- No direct push to
main. All changes go through pull requests. - Squash-merge only. Repo-level setting: merge commits and rebase merges are disabled.
- Linear history required.
- Force pushes blocked, branch deletion blocked.
- Required approvals: 0 — solo-friendly. PRs can land without external review, but they must exist.
- Conversation resolution required before merge.
enforce_admins: false— the maintainer can bypass via the GitHub UI in emergencies. Don't assume CLI bypass works.
Normal change flow
git switch -c <type>/<short-description> # e.g. fix/scad-kwarg, docs/readme-tweak
# ... edit + test ...
git add <specific-files>
git commit -m "..."
git push -u origin HEAD
gh pr create --title "..." --body "..."
gh pr merge --squash --delete-branch # or click squash button in UI
If you forget and git push origin main, GitHub will reject. Don't try to bypass — open a branch + PR.
Release pipeline
Tag-driven. The pipeline is set up via .github/workflows/publish-to-pypi.yml:
- Push to
main→ build job runs (validates the wheel builds). No publish. - Manual
workflow_dispatch→ build + TestPyPI publish (sanity check before tagging). - Push tag
vX.Y.Z→ build + production PyPI publish via OIDC trusted publishing. Uses GitHub Environmentpypi.
Cutting a release:
- On a branch, bump
version = "X.Y.Z"inpyproject.toml. 1b. Sync the Blender addon'sbl_info["version"]to match:python scripts/sync_addon_version.py. The addon ships as bare.pyfiles inside Blender's Python (no package metadata at runtime), so this tuple must be bumped by hand or it drifts.tests/test_version_sync.pyfails the suite if you forget — runpython scripts/sync_addon_version.py --checkto verify. 1c. UpdateCHANGELOG.md: rename the[Unreleased]heading to the new[X.Y.Z] — YYYY-MM-DD, add a fresh empty[Unreleased]above it, and add acomparelink at the bottom. - PR → squash-merge to
main. - From
main: tag with annotated message via heredoc (NOT inline-m "...backticks..."— bash interprets backticks in double-quoted strings as command substitution and eats the names):git tag -a vX.Y.Z -F - <<'EOF' vX.Y.Z Short summary. - Bullet - Bullet EOF git push origin vX.Y.Z - GHA publishes to PyPI within ~1 min. Watch via
gh run list --repo AaronGoldsmith/mcp-printable --limit 3.
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.
- 5d ago First seen · 146 lines · 2,099 tokens per session scan A aee2e56d44d5
mcp-printable CLAUDE.md is an instructions file published in the GitHub repository AaronGoldsmith/mcp-printable (2 stars, last pushed 2mo ago), licensed MIT. It adds 2,099 tokens to every session, about $0.0105 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 2026-08-31.
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).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
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.