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 skills/cohemm/prism/prdnpx skills add cohemm/prism --skill prdgit clone --depth 1 https://github.com/cohemm/prismWhat 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 | $0.00112 | $0.01823 |
| Opus 5 | $0.00056 | $0.00911 |
| Sonnet 5 | $0.00022 | $0.00365 |
| Haiku 4.5 | $0.00011 | $0.00182 |
Grade A, and why
prd 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 2d 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Policy Analysis (Wrapper for analyze)
Takes a PRD file as input, cross-references it against codebase policy documents (ontology) to find policy conflicts and ambiguities. Internally delegates the full multi-perspective analysis to prism:analyze, then post-processes the results into a PM-readable format.
All PRD skill assets must remain self-contained under this directory:
skills/prd/SKILL.mdskills/prd/prompts/post-processor.mdskills/prd/templates/report.mdskills/prd/evals/
Do not require ~/.codex copies or repo-external prompt/template paths when invoking this skill from Claude against the repo source.
Phase 0: Input
Step 0.1: Get PRD File Path
Extract the PRD file path from $ARGUMENTS.
- Path provided → verify file exists via
Read - No path →
AskUserQuestion(header: "PRD File", question: "Please provide the path to the PRD file to analyze.") - File not found → ERROR: "PRD file not found: {path}"
Step 0.2: Generate Session ID
uuidgen | tr '[:upper:]' '[:lower:]' | cut -c1-8
Generate ONCE, reuse throughout. Create state directories for both prd and analyze (shared session ID):
mkdir -p ~/.prism/state/prd-{short-id}
mkdir -p ~/.prism/state/analyze-{short-id}
Step 0.3: Language Detection
- If CLAUDE.md contains a
Languagedirective → use that language - Otherwise → detect from user's input language in this session
- Store as
{REPORT_LANGUAGE}
Phase 0 Exit Gate
- PRD file path confirmed and file existence verified
-
{short-id}generated and~/.prism/state/prd-{short-id}/directory created -
{REPORT_LANGUAGE}determined
→ NEXT: Phase 1 — Create config and invoke analyze
Phase 1: Config & Analyze Invocation
Step 1.1: Read PRD
Read the full PRD file via Read. Identify the title, functional requirements (FR), and non-functional requirements (NFR).
If related files (handoff, constraints, etc.) exist in the same directory, read them as well.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 195 lines · 112 tokens per session scan A 81381e9527ac
prd is a skill published in the GitHub repository cohemm/prism (5 stars, last pushed 3mo ago), licensed MIT. It adds 112 tokens to every session and 1,823 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…