What is skilld CLAUDE.md?

A set of project instructions for skilld, a command-line tool that searches, runs, installs, lists, updates, removes, and verifies instruction packages called Skills.

Use it when developing or testing skilld, its Rust components, or the skilld-harness that reviews generated Skills.

It clarifies the product’s limits, architecture, commands, and testing rules so changes do not blur the boundary between the CLI and the agent using it.

skilld CLAUDE.md — Instructions file by skilld-dev

Install

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.

agentmods

npx agentmods add instructions/skilld-dev/skilld/claude-md

Clone the repo

git clone --depth 1 https://github.com/skilld-dev/skilld

Per session 652 This file is loaded in full into every session.

When invoked 652 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00652	$0.00652
Opus 5	$0.00326	$0.00326
Sonnet 5	$0.00130	$0.00130
Haiku 4.5	$0.00065	$0.00065

Measured 2d ago against content hash b45850b46a45, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skilld 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 2d 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.

CLAUDE.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Read GLOSSARY.md before changing public names, commands, errors, routes, or documentation.

Commands

pnpm install
pnpm test:run
pnpm lint
pnpm typecheck
pnpm build

Use focused commands during development:

pnpm test:loader
pnpm --filter skilld-protocol test:run
pnpm --filter skilld-harness test:run
cargo test --workspace
cargo clippy --workspace --all-targets -- -D warnings

Product boundary

The native skilld CLI searches, runs, installs, lists, views, removes, updates, and verifies Skills. It also manages account authentication and Agent target configuration.

skilld run loads a transient Skill: it prints the Skill and installs nothing. The calling Agent follows the instructions. The CLI never executes them.

The skilld CLI contains no Skill generation logic or Agent runtime.

skilld-harness runs visible skilld-maintained Skills for generation and review. Agents can run the same Skill files directly without the Harness.

Direct runs remain user reviewed. Harness and CI runs enforce strict output checks.

Architecture

crates/skilld-core: shared Rust domain types and Agent target rules
crates/skilld-command: command parsing and local Skill operations
crates/skilld-auth: PKCE, callback, refresh, logout, and keychain contracts
crates/skilld-native: native operating system adapters and executable
crates/skilld-wasi: internal WASIp2 proof
bin and loader: minimal npm native executable selector
packages/cli-*: system specific native npm packages
packages/harness: JavaScript Harness package
packages/protocol: skilld.dev API wire contract
skills: visible skilld-maintained Skills

The npm package has no JavaScript CLI fallback. The WASIp2 package remains private until write behavior reaches native parity.

Artifact delivery

The skilld CLI uses the skilld.dev API for remote Skills. GitHub remains the source of truth.

The CLI verifies exact statement bytes, signatures, digests, and archive structure. Production verification must start from a compiled trusted root key. If no root key exists, fail with TRUSTED_ROOT_UNCONFIGURED.

Read the full file on GitHub · 85 lines

Changes

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.

2d ago First seen · 85 lines · 652 tokens per session scan A b45850b46a45

Subscribe to this mod's changes

skilld CLAUDE.md is an instructions file published in the GitHub repository skilld-dev/skilld (306 stars, last pushed 5d ago), licensed MIT. It adds 652 tokens to every session, about $0.0033 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.

Planning Research Testing

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.

openai/codex · 5,182 tokens

buildNext

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).

microsoft/vscode · 6,785 tokens

skilld CLAUDE.md