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/stephenleo/cship/claude-mdgit clone --depth 1 https://github.com/stephenleo/cshipWrote 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/stephenleo/cship/claude-md)<a href="https://agentmods.dev/instructions/stephenleo/cship/claude-md"><img src="https://agentmods.dev/badge/instructions/stephenleo/cship/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 | $0.00427 | $0.00427 |
| Opus 5 | $0.00214 | $0.00214 |
| Sonnet 5 | $0.00085 | $0.00085 |
| Haiku 4.5 | $0.00043 | $0.00043 |
Grade A, and why
cship 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 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.
What it actually says
cship — AI Agent Instructions
Environment Quirks
- WSL2 ENOENT race: after any
cargo initor file write, verify content with Read before proceeding
Non-Negotiable Code Patterns
- Module interface (never deviate):
pub fn render(ctx: &Context, cfg: &CshipConfig) -> Option<String> - Disabled flag → silent
None(no warn); absent data → explicitmatch+tracing::warn!+None- Exception:
context_barintentionally renders a 0% empty bar (styled viaempty_style) whencontext_windowis absent, rather than returningNone. This is a deliberate UX choice — showing an empty bar is more informative than showing nothing. It usestracing::debug!(notwarn!) because absence is the normal state at session start.
- Exception:
- Never use
?operator on paths that require a warning — use explicitmatch - stdout owned by
main.rsonly; all module diagnostics viatracing::*macros; noeprintln!anywhere - Exception: CLI-action subcommands (e.g.
uninstall,explain) may useprintln!directly — the stdout rule applies to the rendering pipeline only - All config structs:
#[derive(Debug, Deserialize, Default)], all fieldspub Option<T> - Never add
deny_unknown_fieldsto any struct — omitted intentionally on bothContextand config structs so future versions can add fields without breaking deserialization
Before Submitting a PR
- Follow all guidelines in CONTRIBUTING.md before opening or updating a pull request
Project Structure
- Adding a native module: create
src/modules/{name}.rs+ updatesrc/modules/mod.rsonly (2 files max) - Config structs →
src/config.rsonly; ANSI logic →src/ansi.rsonly; threshold styling →ansi::apply_style_with_threshold
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 · 22 lines · 427 tokens per session scan A d82787c93316
cship CLAUDE.md is an instructions file published in the GitHub repository stephenleo/cship (417 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 427 tokens to every session, about $0.0021 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
intelligent-terminal rust-wta.instructions.md
File-scoped conventions for the WTA Rust crate.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
Browser4 CLAUDE.md
Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
dive CLAUDE.md
Instructions for deepnoodle-ai/dive, covering claude.md, project overview, commands, architecture and core types.
NEEDLE CLAUDE.md
Instructions for jedarden/NEEDLE, covering needle project conventions, msrv, module dependency graph, code style and testing.
Isartor copilot-instructions.md
Instructions for isartor-ai/Isartor, covering copilot instructions for isartor, build, test, and lint commands, high-level architecture and key conventions.