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 skills add stefan-stepzero/shipkit --skill shipkit-claude-mdgit clone --depth 1 https://github.com/stefan-stepzero/shipkitWrote 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/skills/stefan-stepzero/shipkit/shipkit-claude-md)<a href="https://agentmods.dev/skills/stefan-stepzero/shipkit/shipkit-claude-md"><img src="https://agentmods.dev/badge/skills/stefan-stepzero/shipkit/shipkit-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.
<a href="https://agentmods.dev/skills/stefan-stepzero/shipkit/shipkit-claude-md"><img src="https://agentmods.dev/badge/skills/stefan-stepzero/shipkit/shipkit-claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00045 | $0.01594 |
| Opus 5.5 | $0.00018 | $0.00638 |
| Sonnet 5.5 | $0.00009 | $0.00319 |
| Haiku 4.5 | $0.00005 | $0.00159 |
Grade A, and why
shipkit-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 1mo 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 — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
shipkit-claude-md
Update CLAUDE.md so future sessions and subagents automatically inherit learnings and context.
When to Invoke
Explicit triggers:
/claude-md <content>— with inline content/claude-md— prompts for what to add/shipkit-claude-md
Natural language triggers:
- "Update CLAUDE.md"
- "Add to CLAUDE.md"
- "Update my claude md"
- "Remember this"
- "Save this for next time"
Important: Never auto-suggest. Only act when user explicitly requests persistence.
Prerequisites
Required:
- Root
CLAUDE.mdexists (installed by Shipkit) - CLAUDE.md has
## Working Preferencesand## Project Learningssections
Optional:
- Subfolder
CLAUDE.mdfiles for folder-specific learnings
Important distinction:
CLAUDE.md→ User-editable (preferences, learnings) — THIS skill edits this file.claude/rules/shipkit.md→ Framework-managed (skills reference, core rules) — DO NOT edit
Process
Step 1: Get the Learning
If invoked with content:
/teach use date-fns instead of moment.js
→ Learning = "use date-fns instead of moment.js"
If invoked without content:
/teach
→ Ask: "What would you like me to remember?"
Step 2: Classify Type
| Learning About... | Type | Target Section |
|---|---|---|
| How Claude behaves | Style | ## Working Preferences |
| Code patterns/libraries | Technical | ## Project Learnings |
Examples:
- "Be more concise" → Style → Working Preferences
- "Use date-fns not moment" → Technical → Project Learnings
- "Always confirm before deleting" → Style → Working Preferences
- "API returns {data:[]} wrapper" → Technical → Project Learnings
Step 3: Determine Scope
Check for existing CLAUDE.md files:
Glob("**/CLAUDE.md")
Present options:
Where should this apply?
[1] Project-wide (root CLAUDE.md)
[2] frontend/ (frontend/CLAUDE.md)
[3] Other path: ___
If user picks a folder without CLAUDE.md, offer to create one.
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.
- 1mo ago First seen · 278 lines · 45 tokens per session scan A 17db4b476987
shipkit-claude-md is a skill published in the GitHub repository stefan-stepzero/shipkit (1 stars, last pushed 3mo ago), licensed MIT. It adds 45 tokens to every session and 1,594 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
skill-learner
Persistent correction system that captures mistakes from skills or Claude behavior and ensures they never repeat across sessions. Use whenever the user indicates something went wrong — "that's wrong", "fix this", "not what I wanted", "learn from this", "don't do that again", "esto está mal", "aprende de esto", "no…
init-project-memory
Use when the user says "init memory", "set up memory", "scaffold memory", "init project memory", or invokes /init-project-memory — creates the .claude/ session memory system in a new project.
session-update
Use when the user says "update session", "log progress", "checkpoint session", or invokes /session-update — especially before /clear or handoff.
milestone
Use when tracking multi-session development work, resuming context from previous conversations, planning phased features, or capturing architectural decisions. Triggers: 'milestone', 'retomar', 'dónde lo dejé', 'seguimos con', 'estado del proyecto', 'qué falta', 'siguiente tarea', 'qué hicimos la última vez'…
compact-manual
Claude Code skill for deterministic context compaction. Compresses the current Claude Code session to the clipboard for a manual rewind+paste workflow. A deterministic alternative to /compact that extracts literal dialog and truncates only tool outputs — no LLM summarization. Use when the user says 'compact the…
context-budget
Use when a coding session is burning context fast, output is drowning in noise, the model keeps forgetting earlier decisions, or the user asks to reduce tokens, stop the verbose narration, work in a huge repo, or make a long session survive. Covers what to read, what to summarize, what to write to disk, and when to…