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/rockcrafters/mason/agents-mdgit clone --depth 1 https://github.com/rockcrafters/masonWrote 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/rockcrafters/mason/agents-md)<a href="https://agentmods.dev/instructions/rockcrafters/mason/agents-md"><img src="https://agentmods.dev/badge/instructions/rockcrafters/mason/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 | $0.01178 | $0.01178 |
| Opus 5 | $0.00589 | $0.00589 |
| Sonnet 5 | $0.00236 | $0.00236 |
| Haiku 4.5 | $0.00118 | $0.00118 |
Grade A, and why
mason 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 3d 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mason
agent kit for chisel / rocks work. a cross-agent skill bundle, portable across claude code, pi, opencode, copilot, and codex.
each capability area is its own skill under mason/skills/. today there are two: mason (the /mason entry point -- routes a request to the right skill, or prints usage) and the substance:
chisel-releases
working on canonical/chisel-releases. command-per-file; commands:
write-slice-- authors + tests + commits chisel slice definition files (SDFs). does not open PRs.review-slice-- read-only review of SDFs against chisel conventions, CI checks, and forward-port rules.
@./mason/skills/chisel-releases/SKILL.md
lives under ./mason/skills/chisel-releases/: commands/, helpers under scripts/, command index schemas/commands.manifest.yaml, and -- once installed -- shared reference shared/CHISEL.md. paths inside command files are relative to the skill's own directory (or, for repo paths like slices/, to the chisel-releases checkout being worked on).
shared/CHISEL.md is not committed -- the source of truth is ./mason/_shared/CHISEL.md, and cli.js materialises it as <skill>/shared/ when installing each skill. in this repo, read/edit mason/_shared/CHISEL.md directly; a mason/skills/*/shared/ dir here is gitignored install fallout, not source.
the deterministic scripts are the backbone, so the commands don't rely on the agent remembering conventions or hand-rolling boilerplate:
- inspect / author:
orientation(where am i, which release/format, which tools are available),deb-list.py(files + deps inside a .deb;--sdfgroups them into a draft SDF -- bins/libs/config/headers/var/copyright, clutter dropped, multiarch dirs globbed, copyright wired (incl. shared-copyright doc-dir symlinks), sorted, ambiguous files left as unplaced comments -- as a deterministic starting point the author refines),try-cut(chisel cut into a temp root),scaffold-test.py(emit a spreadtask.yamlskeleton -- one fresh rootfs per binary-bearing slice, a chroot line per declared binary, so the author fills real functional checks not boilerplate). - check:
check-slice.py(static conventions: sorting, naming, absolute paths, copyright presence, clutter exclusion, arch names, version-gated fields, hint length/style),check-test.py(binary test coverage: warns on no test or a test exercising none of the binaries, else an info summary of untested binaries),check-diff.py(append-only regressions -- removed SDF / slice / path -- theremoved-slicesCI gate; file-pair or--base <ref>via git). - assemble:
review-diff.py --base <ref>finds the changed SDFs in a diff, runs the three checkers, prints findings by severity with a verdict, exits non-zero on anyblock. this is the CI-callable PR-review bot; it needs no agent.
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.
- 3d ago First seen · 35 lines · 1,178 tokens per session scan A 60b888e1e63b
mason AGENTS.md is an instructions file published in the GitHub repository rockcrafters/mason (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,178 tokens to every session, about $0.0059 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).
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.
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.
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 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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.