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/slopstopper/plumb-line/agents-mdgit clone --depth 1 https://github.com/slopstopper/plumb-lineWrote 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/slopstopper/plumb-line/agents-md)<a href="https://agentmods.dev/instructions/slopstopper/plumb-line/agents-md"><img src="https://agentmods.dev/badge/instructions/slopstopper/plumb-line/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 | $0.01774 | $0.01774 |
| Opus 5 | $0.00887 | $0.00887 |
| Sonnet 5 | $0.00355 | $0.00355 |
| Haiku 4.5 | $0.00177 | $0.00177 |
Grade A, and why
plumb-line 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 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — plumb-line
Instructions for coding agents working in this repository, and the map a new contributor needs to find everything else.
This file deliberately points rather than copies. Every durable fact about this repo already lives in a committed document; restating values here would create a second source of truth that drifts — the failure this repo exists to prevent. What is written here is what you cannot get by reading one file: which file, and that it matters.
Where things are written down
| You need | It is in |
|---|---|
| How to build and test each component | DEVELOPMENT.md |
| How to contribute, and what a PR must satisfy | CONTRIBUTING.md |
| How releases are cut and published | RELEASING.md |
| The nine principles this project enforces — and is held to | reference/portable-principles.md |
| The envelope schema (the formal spec) | primitives/SPEC.md |
| The two API shapes, JS vs Python | docs/api.md |
| Cross-language parity, and the case table that enforces it | primitives/PARITY.md, primitives/conformance/cases.json |
| What is guaranteed, and what is only tamper-evident | docs/threat-model.md, SECURITY.md |
| Exact-valued global constraints (versions, floors, contracts) | docs/constraints.md |
| Why a past decision was made | docs/adr/ — append-only |
| What is planned, and how the backlog is organised | ROADMAP.md |
| This repo's tracking vocabulary and modules | docs/tracking-dialect.md |
Four things that are load-bearing
Each is documented above. They are repeated here as warnings because each is something an agent gets wrong by acting on a reasonable default.
- There is no root test command. No root
package.json. Each component is tested from its own directory. Running "the tests" from the repo root tests nothing. SeeDEVELOPMENT.md. - Parity is the central invariant. JS and Python must behave
identically. When you change combination or audit behaviour, change
both implementations and add a row to
cases.json. A divergence failing one suite is the system working. Never "fix" parity by editing prose — fix the code or the case table. - This repo is held to its own principles. The rules the audit skill
applies to other people's code apply here. Don't launder uncertainty,
hardcode a prior, or overstate maturity; use the maturity vocabulary
(
current/planned), not aspirational claims. - New behaviour needs a failing test first. Enforcement is proven by tests, not asserted.
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 · 140 lines · 1,774 tokens per session scan A fcc17f8d70d9
plumb-line AGENTS.md is an instructions file published in the GitHub repository slopstopper/plumb-line (4 stars, last pushed 4d ago), licensed Apache-2.0. It adds 1,774 tokens to every session, about $0.0089 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
craftsman-marketplace CLAUDE.md
Claude Code instructions for gul-labs/craftsman-marketplace, covering claude.md, editing rules and design principles (non-negotiable).
craft-skills CLAUDE.md
Instructions for mikestangdevs/craft-skills, covering claude.md, what this repo is, commands, architecture and bucket organization & governance.
stockbit-mcp CLAUDE.md
Claude Code instructions for INo-xious/stockbit-mcp, covering claude.md, what this is, commands, the map and three invariants. do not break them; each has a test.
logic-lens GEMINI.md
Instructions for hyhmrright/logic-lens, covering logic-lens — developer guide (gemini cli), invoking skills, installation, project layout and key conventions.
curie CLAUDE.md
Claude Code instructions for curie-eng/curie, covering one entry point: curie, release train selection and architecture decision records (adrs).
evolve-loop GEMINI.md
Gemini CLI instructions for mickeyyaya/evolve-loop, covering project instructions (gemini cli), skill discovery, runtime adapter (tier-1-hybrid), tool name translation and invariants (apply to gemini context too).