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 jakeefr/prism --skill prism-advisegit 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/skills/jakeefr/prism/prism-advise)<a href="https://agentmods.dev/skills/jakeefr/prism/prism-advise"><img src="https://agentmods.dev/badge/skills/jakeefr/prism/prism-advise.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 5.1 | $0.00033 | $0.00671 |
| Opus 5 | $0.00016 | $0.00336 |
| Sonnet 5 | $0.00007 | $0.00134 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade A, and why
prism-advise 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 8d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
prism-advise
Get concrete CLAUDE.md recommendations based on real session data.
When to use
When the user asks to audit their CLAUDE.md, fix their CLAUDE.md, improve their CLAUDE.md, or understand what is wrong with it.
Before running
First check if PRISM is installed:
prism --version
If the command is not found, install it first:
pip install prism-cc
Then verify it installed correctly:
prism --version
Once confirmed installed, proceed with the advise command.
Usage
Run the advisor for the current project:
prism advise --project .
For a different project:
prism advise --project <path>
From an agentsview database (real API token counts, richer data):
prism advise --source agentsview
prism advise --source agentsview --agentsview-db /path/to/sessions.db
DB path resolution: AGENTSVIEW_DATA_DIR → AGENT_VIEWER_DATA_DIR → ~/.agentsview/sessions.db.
Note: --project cannot be used with --source agentsview.
Interpreting the output
PRISM prints recommendations with four action types:
- ADD means a new rule should be added to CLAUDE.md. Session data shows a problem that no existing rule addresses. Example: retry loops caused by missing non-interactive flags.
- TRIM means lines should be removed from CLAUDE.md. Usually personality or tone instructions past line 80 that waste tokens on every tool call.
- WARN means an existing rule is being violated in sessions. The rule exists but Claude is not following it. May need stronger phrasing or better placement.
- RESTRUCTURE means rules should be moved. Either to subdirectory CLAUDE.md files (if they only apply to one part of the codebase) or to the top/bottom of the file (if critical rules are buried in the attention dead zone).
Each recommendation includes an impact level (High, Medium, Low) and evidence from actual session data.
Applying recommendations
If the user wants to apply the ADD recommendations automatically:
prism advise --project . --apply
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.
- 8d ago First seen · 92 lines · 33 tokens per session scan A 6d6c1b6de353
prism-advise is a skill published in the GitHub repository jakeefr/prism (22 stars, last pushed 3mo ago), licensed MIT. It adds 33 tokens to every session and 671 once invoked, about $0.0002 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…