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 agentmods add instructions/jakeefr/prism/claude-mdgit clone --depth 1 https://github.com/jakeefr/prismWrote 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/instructions/jakeefr/prism/claude-md)<a href="https://agentmods.dev/instructions/jakeefr/prism/claude-md"><img src="https://agentmods.dev/badge/instructions/jakeefr/prism/claude-md.svg" alt="Measured on agentmods" 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 | $0.00917 | $0.00917 |
| Opus 5 | $0.00458 | $0.00458 |
| Sonnet 5 | $0.00183 | $0.00183 |
| Haiku 4.5 | $0.00092 | $0.00092 |
Grade A, and why
prism 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 3d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRISM
Post-session diagnostic CLI for Claude Code. Parses session data, scores it across five health dimensions, and surfaces actionable fixes via a CLI report, interactive TUI, or HTML dashboard.
Health Dimensions
- Token Efficiency — compaction rate, token waste, CLAUDE.md bloat
- Tool Health — retry loops, interactive commands, migration edits, consecutive failures
- Context Hygiene — compaction frequency, mid-task compaction, context pressure
- CLAUDE.md Adherence — rule extraction, violation detection, attention curve
- Session Continuity — truncation, context loss across continuations
Architecture
JSONL files ─┐
├─ SessionDataSource ─→ analyzer ─→ advisor ─→ CLI / TUI / dashboard
agentsview DB┘
The SessionDataSource protocol (datasource.py) abstracts over two backends:
JSONLDataSource— reads raw.jsonlsession files from~/.claude/projects/AgentsviewDataSource— reads from the agentsview SQLite DB
The parser produces typed records (UserRecord, AssistantRecord, SystemRecord).
The analyzer computes metrics from those records. The advisor generates CLAUDE.md
recommendations from the metrics. The CLI, TUI, and dashboard are thin presentation
layers.
Key Files
| File | Purpose |
|---|---|
prism/parser.py |
JSONL parsing, record dataclasses. No analysis. |
prism/analyzer.py |
All metrics computation. No I/O (except CLAUDE.md read). |
prism/advisor.py |
Recommendation generation from analyzer output. |
prism/datasource.py |
SessionDataSource protocol + JSONLDataSource. |
prism/agentsview.py |
AgentsviewDataSource — SQLite adapter for agentsview. |
prism/cli.py |
Typer CLI. Thin layer calling analyzer/advisor/app. |
prism/app.py |
Textual TUI. Imports widgets from prism/widgets/. |
prism/dashboard.py |
Single-file HTML dashboard generator. |
Data Sources
JSONL (default):
prism analyze # reads ~/.claude/projects/
prism analyze --base-dir /other/path # override base directory
prism analyze --project /path/to/proj # single project
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.
- 3d ago First seen · 93 lines · 917 tokens per session scan A 68173a75d79f
prism CLAUDE.md is an instructions file published in the GitHub repository jakeefr/prism (23 stars, last pushed 2mo ago), licensed MIT. It adds 917 tokens to every session, about $0.0046 per session on Opus 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 2026-08-30.
Other instructions, from other repositories
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.