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/morloc-project/morloc/claude-mdgit clone --depth 1 https://github.com/morloc-project/morlocWrote 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/morloc-project/morloc/claude-md)<a href="https://agentmods.dev/instructions/morloc-project/morloc/claude-md"><img src="https://agentmods.dev/badge/instructions/morloc-project/morloc/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 | $0.00633 | $0.00633 |
| Opus 5 | $0.00316 | $0.00316 |
| Sonnet 5 | $0.00127 | $0.00127 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
morloc 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code when working with this repository.
Project Overview
Morloc is a multi-lingual typed workflow language enabling function composition across Python, C++, and R under a unified type system.
General Rules
- Errors are ALWAYS serious
- Do not ignore an error because it is pre-existing
- If an unexpected error is found, stop and describe it
- Performance is critical
- Morloc programs may run for days or nanoseconds
- All between process communication must be as fast as possible (no more than a few microseconds), and yet the processes must accommodate very large packets and programs that run for a very long time.
Checking code
After making a substantial change to the Haskell code, run:
$ stack install --no-run-tests $ stack test morloc:morloc-test # This is the usual test
To run the full heavy integrated test suite, run:
$ stack test # ONLY do this at the very end of a session; IT IS EXPENSIVE
If you make any change to the non-haskell code in data/, then you MUST run
morloc init -f. This will rebuild shared libraries, the nexus executable, and
language bindings.
- Stack test runs unit tests and golden-tests
- Golden-tests are full morloc programs
- Each golden test is in the path @test-suite/golden-tests/
- These tests produce build errors in
build.errand runtime errors inobs.err. These outputs are VITAL to debugging errors.
If the required morloc libraries may have changed, you may run:
$ morloc install --force
Other rules
Never ignore errors
Git Rules
- DO NOT commit code
- DO NOT use any destructive git commit
- DO USE for
git logandgit diffvariants
Haskell Coding Style
- comments should be sparse and succinct
- comments should explain complex code and a rationale
- avoid non-total functions when possible
Testing Conventions
- tests should be written for all new features
- tests may be unit tests or integrated golden-tests
- test strategies, and justification for why they cover the new feature, should be provided
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 · 86 lines · 633 tokens per session scan A fd8dedd4edca
morloc CLAUDE.md is an instructions file published in the GitHub repository morloc-project/morloc (216 stars, last pushed 5d ago), licensed Apache-2.0. It adds 633 tokens to every session, about $0.0032 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 2026-08-30.
Other instructions, from other repositories
kara CLAUDE.md
Claude Code instructions for karalang/kara, covering claude.md, commands, branch management, claiming a bug (multi-session coordination) and architecture.
harn AGENTS.md
AGENTS.md instructions for burin-labs/harn, covering agents.md, ownership, working agreement, harn scripts and setup and resource isolation.
Lesma AGENTS.md
Instructions for alinalihassan/Lesma, covering agents.md — lesma project guide for ai agents, what lesma is, project layout, wall-clock benchmark (benchmark suite) and compilation pipeline.
harn CLAUDE.md
Claude Code instructions for burin-labs/harn, a project described as: Harn is a programming language and runtime for building AI agents.
sigil-lang CLAUDE.md
Claude Code instructions for Daemoniorum-LLC/sigil-lang, covering sigil language - agent guide, the canonical compiler, run sigil programs, run tests and why rust compiler?.
patchloom AGENTS.md
AGENTS.md instructions for patchloom/patchloom, covering agents.md, project overview, dev commands, git hygiene and release prs (release-please).