Synapse: Skill for Claude Code

.claude/skills/project-insights/SKILL.md

project-insights is a skill for Claude Code from JosephOIbrahim/Synapse. It costs 0 tokens per session (1,257 once invoked), scanned A, original, MIT.

A tool for analyzing past coding-agent sessions within the current project folder. It reads session records such as messages, tools used, languages, edits, commits, and the first request.

In plain words
What is it for?
Use it to review work patterns, past requests, tool usage, code changes, and project activity. A broad option can also include sessions from parent folders.
Why use it?
It prevents history from other projects from influencing the analysis. By default, it only considers sessions whose project path exactly matches the current project.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is JosephOIbrahim/Synapse's own configuration. It tells Claude Code how to work on Synapse 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 Synapse configures →

Reuse

Borrowing it

Nothing to install: this file belongs to JosephOIbrahim/Synapse. 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/JosephOIbrahim/Synapse/master/.claude/skills/project-insights/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/JosephOIbrahim/Synapse

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 project-insights

README.md
[![agentmods](https://agentmods.dev/badge/skills/josephoibrahim/synapse/project-insights.svg)](https://agentmods.dev/skills/josephoibrahim/synapse/project-insights)
Your own site
<a href="https://agentmods.dev/skills/josephoibrahim/synapse/project-insights"><img src="https://agentmods.dev/badge/skills/josephoibrahim/synapse/project-insights.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,257 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00000 $0.01257
Opus 5 $0.00000 $0.00629
Sonnet 5 $0.00000 $0.00251
Haiku 4.5 $0.00000 $0.00126

Measured 7d ago against content hash 704de7d4be6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

project-insights 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 7d 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/skills/project-insights/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project-Scoped Insights

Analyze session history filtered to the CURRENT project only. Prevents cross-project context pollution.

Instructions

1. Detect Scope

Determine the current working directory. This is your project scope. Extract the project name from the last path segment.

Check for a --broad flag in the user's invocation. If present, include sessions whose project_path is a parent of the current directory (e.g., C:\Users\User sessions when running from C:\Users\User\SYNAPSE). Default behavior: strict match only.

2. Read Session Metadata

Read ALL .json files from ~/.claude/usage-data/session-meta/. Each file contains:

  • session_id — UUID matching the filename
  • project_path — Working directory when the session ran
  • start_time, duration_minutes, user_message_count, assistant_message_count
  • tool_counts — Object of tool name to usage count
  • languages — Object of language name to file count
  • git_commits, git_pushes, lines_added, lines_removed, files_modified
  • first_prompt — Truncated first user message

Use the Bash tool to read all files efficiently:

python -c "
import json, glob, os
sessions = []
for f in glob.glob(os.path.expanduser('~/.claude/usage-data/session-meta/*.json')):
    with open(f, encoding='utf-8') as fh:
        sessions.append(json.load(fh))
print(json.dumps(sessions))
"

3. Filter to Current Project

Apply the filter:

  • Strict (default): Keep sessions where project_path exactly equals the current working directory (case-insensitive, normalize path separators)
  • Broad (--broad): Also include sessions where the current working directory starts with project_path (i.e., project_path is a parent directory)

Use Python for filtering:

python -c "
import json, sys, os

cwd = os.getcwd().replace('/', os.sep).rstrip(os.sep).lower()
broad = '--broad' in sys.argv
sessions = json.loads(sys.argv[-1])

matched = []
for s in sessions:
    sp = s.get('project_path', '').replace('/', os.sep).rstrip(os.sep).lower()
    if sp == cwd:
        matched.append(s)
    elif broad and cwd.startswith(sp + os.sep):
        matched.append(s)

print(json.dumps(matched, indent=2))
" [BROAD_FLAG] '[SESSION_JSON]'

Read the full file on GitHub · 143 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. 7d ago First seen · 143 lines · 0 tokens per session scan A 704de7d4be6c

Subscribe to this mod's changes

project-insights is a skill published in the GitHub repository JosephOIbrahim/Synapse (10 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,257 tokens. 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.

Related

Other skills, from other repositories

dcc-mcp-core

Foundation library for the DCC Model Context Protocol (MCP) ecosystem. Provides Rust-powered action management, skills system, IPC transport, MCP Streamable HTTP server (2025-03-26 spec, with 2025-06-18 and 2025-11-25 awareness), sandbox security, shared memory, screen capture, USD scene support, and telemetry for…

dcc-mcp/dcc-mcp-core · 109 tokens

dcc-cua

A routing guide for controlling application interfaces through the project’s DCC-CUA system. DCC applications are digital-content tools such as Maya, Blender, and Houdini.

dcc-mcp/dcc-mcp-core · 131 tokens

marketplace-publish-extension

Infrastructure skill — publish (register/update) an extension package to a marketplace catalog. Reads the extension's SKILL.md frontmatter, constructs a CatalogEntry, and upserts it into the target marketplace.json. Optionally commits and pushes when the catalog source is a git repository. Use after scaffolding an…

dcc-mcp/dcc-mcp-core · 88 tokens

example-layered-skill

Example skill — reference implementation of the internal layered architecture pattern (Tools / Services / Utils) for complex skills with shared business logic. Use as a template when a skill outgrows a single scripts/execute.py file. Not intended for production use — see docs/guide/skills.md for the architectural…

dcc-mcp/dcc-mcp-core · 70 tokens

marketplace-create-extension

Infrastructure skill — scaffold a new marketplace extension package (SKILL.md + tools.yaml + scripts/) with MIT-0 licensing. Use when creating a publishable marketplace entry for any DCC host. Not for editing existing extensions or driving live DCC scenes — use domain skills for that.

dcc-mcp/dcc-mcp-core · 62 tokens

clawhub-compat

Example skill — demonstrates full compatibility with the ClawHub/OpenClaw skill format. Use as a reference when creating skills for both the dcc-mcp-core ecosystem and ClawHub marketplace. Not intended for production use — this is an authoring reference only.

dcc-mcp/dcc-mcp-core · 59 tokens