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.
git clone --depth 1 https://github.com/tznthou/claude-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/commands/tznthou/claude-prism/pi-plan)<a href="https://agentmods.dev/commands/tznthou/claude-prism/pi-plan"><img src="https://agentmods.dev/badge/commands/tznthou/claude-prism/pi-plan/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/commands/tznthou/claude-prism/pi-plan"><img src="https://agentmods.dev/badge/commands/tznthou/claude-prism/pi-plan.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00078 | $0.03260 |
| Opus 5 | $0.00039 | $0.01630 |
| Sonnet 5 | $0.00016 | $0.00652 |
| Haiku 4.5 | $0.00008 | $0.00326 |
Grade B, and why
pi-plan scanned grade B with 1 finding 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 9d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat > ".claude/pi-plans/<slug>.md" << 'PLAN_EOF' How it starts
The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Generation
Analyze the codebase and generate a structured implementation plan with cross-provider architectural consultation. Use this when multiple viable approaches exist and external perspectives add value — not for simple task breakdown.
Execution
Dispatch rules (v0.13.0+): For parallel provider consultation, use the
Agenttool withsubagent_type: "general-purpose"to spawn two parallel sub-agents — NOT twoBashtool calls in a single main-conversation response. Main-conversation Bash is a structural FIFO queue: the second Bash waits for the first to finish (delta ≈ first_execprecisely, measured N=7 across two capacity slots), which defeats the parallel intent. Sub-agent fan-out dispatches Bash calls truly in parallel (median delta 2.8s, N=13), saving roughly 28% wall-clock on a two-provider call.Inside each sub-agent, run
call-codex.sh/call-gemini.shin foreground synchronous mode withtimeout: 600000(Bash tool's 10-minute ceiling). Do not use&,nohup, orrun_in_background: true— Claude Code 2026-04+ has an auto-background child-lifecycle regression that silently kills the child (output file stays 0 bytes). If a sub-agent's Bash returns empty stdout, the Bash template below falls back to reading the caller-owned$OUT_PATHfile (v0.14.3+, wrappertees here viaCLAUDE_PRISM_OUT_TMP).
1. Parse arguments
$ARGUMENTS is the task description. If it's too vague (less than ~10 words and no clear objective), use AskUserQuestion to clarify:
- What is the desired end state?
- Are there constraints (tech stack, scope)?
- Should external providers be consulted? (default: yes if available)
2. Analyze the codebase
Use Read, Glob, and Grep tools to understand the current state:
- Project structure and key directories
- Relevant existing code (files related to the task)
- Dependencies and configuration
- Existing tests and CI setup
3. Detect domain
If there are existing files that will be modified, detect the domain:
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.
- 9d ago First seen · 234 lines · 78 tokens per session scan B 7f4181894b49
pi-plan is a command published in the GitHub repository tznthou/claude-prism (10 stars, last pushed today), licensed MIT. It adds 78 tokens to every session and 3,260 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
conventions-check
Check AGENTS.md, CLAUDE.md, and the projected agent artifacts (skills, subagents, commands) against the repo's conventions.
register-plugin-asset
A project command for adding a distributable command, agent, or agent skill to a plugin manifest, the file that lists what a plugin provides.
challenge
Adversarial review — run pre-mortem, war-game, and logic-torturing analysis on current changes.
logic-diff
Check two code versions for semantic equivalence — use after a refactor or rewrite.
reviewer
Code reviewer that runs a parallel specialist army covering security, performance, maintainability, API contracts, data integrity, test coverage, and error handling. Trigger on code review, review, PR review, pull request, or review army.
README
Repo-development slash commands (NOT part of the distributed plugin surface).