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/jankowskim/lory/claude-mdgit clone --depth 1 https://github.com/jankowskim/loryWrote 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/jankowskim/lory/claude-md)<a href="https://agentmods.dev/instructions/jankowskim/lory/claude-md"><img src="https://agentmods.dev/badge/instructions/jankowskim/lory/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 | $0.00748 | $0.00748 |
| Opus 5 | $0.00374 | $0.00374 |
| Sonnet 5 | $0.00150 | $0.00150 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
lory 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 4d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lory — Structured Decision Records
This repository uses Lory for structured decision records.
Before Modifying Code
- Run
lory context <path>to understand why the code is shaped this way. - Run
lory rejected <path>to avoid re-exploring dead ends.
Commit Format
Every commit must explain WHY, not WHAT. Use Lory trailers:
Short description of WHY this change was made
Constraint: Any rules this change must follow
Rejected: Alternative approach | why it was rejected
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: Warning for future maintainers
Tested: What was tested
Not-tested: What was not tested
Run lory validate --count 1 after committing to verify format.
Commands
lory context <path> # Full decision context for a file/directory
lory constraints <path> # Active constraints affecting this code
lory rejected <path> # Previously rejected alternatives
lory directives <path> # Forward-looking warnings from past authors
lory stale # Detect outdated assumptions
lory review --base main # Check changes against decision context
lory validate --count 5 # Check recent commits for proper format
lory export [paths] # Export decision context as JSONL or text
lory preflight # Combined pre-PR check (validate+stale+coverage+review)
Beads Issue Tracker
This project uses bd (beads) for issue tracking. Run bd prime to see full workflow context and commands.
Quick Reference
bd ready # Find available work
bd show <id> # View issue details
bd update <id> --claim # Claim work
bd close <id> # Complete work
Rules
- Use
bdfor ALL task tracking — do NOT use TodoWrite, TaskCreate, or markdown TODO lists - Run
bd primefor detailed command reference and session close protocol - Use
bd rememberfor persistent knowledge — do NOT use MEMORY.md files
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.
- 4d ago First seen · 92 lines · 748 tokens per session scan A 427b2149f3c3
lory CLAUDE.md is an instructions file published in the GitHub repository jankowskim/lory (2 stars, last pushed 3mo ago), licensed MIT. It adds 748 tokens to every session, about $0.0037 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
warrant AGENTS.md
Instructions for s0fractal/warrant, covering agent & contributor conduct (governance-critical), hard rules, the human's role and precedent (why this file exists).
adc AGENTS.md
Instructions for dbrattli/adc, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
redraft CLAUDE.md
Instructions for KaelinGraf/redraft, covering redraft (engine), running tests, rebuilding the ui and the organizing protocol.
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.