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 jkm-4314/claude-code-skills --skill init-project-memorygit clone --depth 1 https://github.com/jkm-4314/claude-code-skillsWrote 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/jkm-4314/claude-code-skills/init-project-memory)<a href="https://agentmods.dev/skills/jkm-4314/claude-code-skills/init-project-memory"><img src="https://agentmods.dev/badge/skills/jkm-4314/claude-code-skills/init-project-memory/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/jkm-4314/claude-code-skills/init-project-memory"><img src="https://agentmods.dev/badge/skills/jkm-4314/claude-code-skills/init-project-memory.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 | $0.00048 | $0.02540 |
| Opus 5.5 | $0.00019 | $0.01016 |
| Sonnet 5.5 | $0.00010 | $0.00508 |
| Haiku 4.5 | $0.00005 | $0.00254 |
Grade A, and why
init-project-memory 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 — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Initialize Project Memory System
You are scaffolding the .claude/ session memory system into a new project. This creates the file structure that the session-start, session-update, and session-end skills depend on.
Step 1: Pre-Flight Checks
- Verify this is a git repository (
git rev-parse --git-dir). If not, stop and tell the user — the session system is git-grounded. - Check if
.claude/SESSION_LOG.mdalready exists. If it does, warn the user and ask before overwriting:"This project already has a session memory system. Overwrite it? (This won't touch settings.json or skills/)"
Step 2: Gather Project Info
Ask the user:
- Project name — e.g., "Acme Widget Manager"
- Short identifier — e.g.,
widget-mgr(used in headers) - One-line description — what the project is
- Tech stack — e.g., "FastAPI + React + PostgreSQL + Docker" (used in CONTEXT.md template)
- Should I create a CLAUDE.md? — if one doesn't already exist
If the user says "just use defaults" or similar, infer what you can from the repo (package.json, pyproject.toml, docker-compose.yml, etc.) and fill in reasonable defaults. Confirm before writing.
Step 3: Create Directory Structure
mkdir -p .claude
Step 4: Write Template Files
Create each file. Do NOT overwrite files that already exist (e.g., settings.json, settings.local.json, existing skills) unless the user explicitly asked to reset.
.claude/CONTEXT.md
# {{Project Name}} (`{{short-id}}`) - Project Context
> **Last Updated:** {{MM-DD-YYYY}}
> **Version:** {{version or "0.1.0"}}
> **Status:** {{status or "In development"}}
---
## What This Project Is
{{One-line description. Expand with 2-3 sentences about purpose, users, and scope.}}
---
## Technology Stack
{{Tech stack details — backend, frontend, database, infrastructure.}}
---
## Architecture Overview
{{High-level architecture. Fill in as the project takes shape.}}
---
## Development Environment
{{How to run the project locally. Commands, ports, prerequisites.}}
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 · 313 lines · 48 tokens per session scan A d28dfbff6ccc
init-project-memory is a skill published in the GitHub repository jkm-4314/claude-code-skills (4 stars, last pushed 5mo ago), licensed MIT. It adds 48 tokens to every session and 2,540 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…
shipkit-work-memory
Log session progress and save resume state. Infers from conversation and git. Triggers: 'log progress', 'session summary', 'checkpoint', 'save progress', 'end session'.
shipkit-claude-md
Update CLAUDE.md with learnings, preferences, or project context. Use when user says "update claude.md", "add to claude.md", or wants to persist something.
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…