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.
curl -O https://raw.githubusercontent.com/JosephOIbrahim/Synapse/master/.claude/skills/project-insights/SKILL.mdgit clone --depth 1 https://github.com/JosephOIbrahim/SynapseWrote 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/josephoibrahim/synapse/project-insights)<a href="https://agentmods.dev/skills/josephoibrahim/synapse/project-insights"><img src="https://agentmods.dev/badge/skills/josephoibrahim/synapse/project-insights/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/josephoibrahim/synapse/project-insights"><img src="https://agentmods.dev/badge/skills/josephoibrahim/synapse/project-insights.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.01257 |
| Opus 5.5 | $0.00000 | $0.00503 |
| Sonnet 5.5 | $0.00000 | $0.00251 |
| Haiku 4.5 | $0.00000 | $0.00126 |
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 2mo 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 — 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 filenameproject_path— Working directory when the session ranstart_time,duration_minutes,user_message_count,assistant_message_counttool_counts— Object of tool name to usage countlanguages— Object of language name to file countgit_commits,git_pushes,lines_added,lines_removed,files_modifiedfirst_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_pathexactly equals the current working directory (case-insensitive, normalize path separators) - Broad (
--broad): Also include sessions where the current working directory starts withproject_path(i.e.,project_pathis 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]'
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.
- 2mo ago First seen · 143 lines · 0 tokens per session scan A 704de7d4be6c
project-insights is a skill published in the GitHub repository JosephOIbrahim/Synapse (12 stars, last pushed today), 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.
Other skills, from other repositories
seedance-vfx
This skill should be used when the user asks for VFX, particles, energy, destruction, transformation, weather effects, magical effects, explosions, smoke, fire, water, or physically plausible effects in Seedance 2.0.
frame-liquid-bg-hero
WebGL-style fluid displacement background with a quote overlay, suited to video intros, landing heroes, or posters.
frame-glitch-title
Digital glitch, chromatic offset, and data-corruption title frame for video transitions or cyberpunk heroes.
vfx-text-cursor
Cursor light trail, chromatic rays, and directional flares for word-by-word quote reveals in video intros.
vfx-text-cursor
A video or hero-frame effect where a cursor reveals a sentence character by character with coloured trails, light streaks, and a final shimmer.
seedance-vfx
This skill should be used when the user asks for VFX, particles, energy, destruction, transformation, weather effects, magical effects, explosions, smoke, fire, water, or physically plausible effects in Seedance 2.0.