sshlg-skills: Instructions file for Claude Code

CLAUDE.md

sshlg-skills CLAUDE.md is an instructions file for Claude Code from ssheleg/sshlg-skills. It costs 1,424 tokens per session, scanned B, original, MIT.

Repository-specific instructions for the ssheleg skill family, including its launcher, submodules, routing rules, and test gate. A submodule is a repository included at a fixed version inside another repository.

In plain words
What is it for?
Use them when editing or testing this repository, validating pinned components, updating its routing block, or checking that offline tests pass.
Why use it?
They document the local rules and checks needed to change this repository safely, including how its operator-owned file is handled.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is ssheleg/sshlg-skills's own configuration. It tells Claude Code how to work on sshlg-skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sshlg-skills configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ssheleg/sshlg-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ssheleg/sshlg-skills/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ssheleg/sshlg-skills

Made for: Claude Code.

Wrote 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.

agentmods badge for sshlg-skills CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ssheleg/sshlg-skills/claude-md/github.svg)](https://agentmods.dev/instructions/ssheleg/sshlg-skills/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ssheleg/sshlg-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/ssheleg/sshlg-skills/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for sshlg-skills CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ssheleg/sshlg-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/ssheleg/sshlg-skills/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,424 This file is loaded in full into every session.
When invoked 1,424 The same file — it is already loaded in full.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01424 $0.01424
Opus 5.5 $0.00570 $0.00570
Sonnet 5.5 $0.00285 $0.00285
Haiku 4.5 $0.00142 $0.00142

Measured today against content hash ae8f99335998, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

sshlg-skills CLAUDE.md scanned grade B with 1 finding 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 today.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

`visibility` edits to `~/.claude/settings.json`, `~/.codex/config.toml`,
CLAUDE.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md: sshlg-skills

House rules for this repository. Global language, quality, autonomy and routing belong to the host's instruction files; do not duplicate them here.

Start here

Read docs/HANDOFF.md for the current entry and dated receipts. Apply the standing repository handoff instruction to every task. Read the retrospective's standing instructions in full before work (that section only, about 12 KB; query the run stamps below it with grep, never read them whole) and coordination before editing a shared registry. DOCMAP owns single homes and propagation rules; backlog owns outstanding work; verification owns delivery evidence.

What this repo owns

A zero-dependency Node launcher and the family members as pinned git submodules. skills.json is the member inventory; each member owns its doctrine. The hub owns the routing block that writes into operator-owned instruction files. Those files may have no version control: every write must be recoverable.

Gate and evidence

npm test          # structural validator and discovered test suites

DOCMAP's ratchets are computed by that run, never carried from another revision. python3 test/check_pins.py queries npm and stays outside the offline gate. Numbers are measured; named commands run and named files resolve. Evidence belongs to the checked artifact, and a historical receipt is not a current runtime claim.

Invariants

  • One channel per agent. Plain ~/.claude/skills/<id> copies shadow plugins and freeze their version. install and update prune them after every skills-CLI run.
  • Live document addresses resolve. test/doc_refs.py extracts and resolves; test/validate.py owns the live/dated corpus. Live dead commands and paths fail; dated records are counted and disclosed, not rewritten. Negative controls cover the claim classes and an empty corpus. Quote a dead command as dead, never runnable.
  • Submodule URLs are HTTPS. An SSH URL works for a key holder and fails for other installers. test/validate.py rejects it; CI has a negative self-test.
  • The pin is the promise. The committed member version, skills.json, submodule pointer and README table agree. A checkout installs the advertised version.
  • The operator's wording wins. authored entries outrank packaged text; routers reports drift. Only --adopt replaces wording, one router at a time, retaining what it replaced.
  • Inspect executable input. The hygiene guard's executablePart() removes non-shell heredoc bodies and whole-line comments, but retains shell heredocs and quoted invocations, including bash -c. Quoting must not bypass bareName checks.
  • Guards decide in pure modules; hooks move bytes. lib/guard.js, lib/hygiene.js, lib/gitdiscard.js and lib/repogate.js decide from payloads, fixtured without a HOME; filesystem access is confined to backup boundaries, and the one probe (git status for the paths a destructive git command names) is run by the hook, bounded, and fails open. A hook entry's if filter is best-effort and fails open on unparsed commands; do not rely on it.
  • Hooks fail silent; refusals name a remedy. A malformed payload must not break other sessions. test/hooks_e2e_test.js asserts both through real script processes. Claude Code 2.1.295 added onFailure: "block"; family hooks keep the default continue on purpose: adding block is not hardening, it breaks this rule.

Read the full file on GitHub · 91 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.

  1. today Changed ae8f99335998
  2. yesterday Changed · +8 lines · +193 tokens per session fad954b10429
  3. 8d ago Changed · +1 lines · +30 tokens per session a8462849d99a
  4. 16d ago Changed · +3 lines · +91 tokens per session 664ebd52fa1d
  5. 18d ago Changed · +3 lines · +69 tokens per session scan A → B 0039f8f6a40e
  6. 19d ago Changed · -50 lines · -820 tokens per session 3a6620f49a1f
  7. 26d ago Changed · +1 tokens per session 039f8214630e
  8. 1mo ago Changed · +5 lines · +53 tokens per session e97b95f27d5d
  9. 1mo ago First seen · 121 lines · 1,807 tokens per session scan A f78f8f6b8bb1

Subscribe to this mod's changes

sshlg-skills CLAUDE.md is an instructions file published in the GitHub repository ssheleg/sshlg-skills (12 stars, last pushed yesterday), licensed MIT. It adds 1,424 tokens to every session, about $0.0057 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

data-scientist copilot-instructions.md

Repository instructions for a data-science workflow in GitHub Copilot, covering datasets, statistics, and analysis files.

realnghon/data-scientist · 373 tokens

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).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens