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-research)<a href="https://agentmods.dev/commands/tznthou/claude-prism/pi-research"><img src="https://agentmods.dev/badge/commands/tznthou/claude-prism/pi-research/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-research"><img src="https://agentmods.dev/badge/commands/tznthou/claude-prism/pi-research.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 | $0.00014 | $0.02271 |
| Opus 5 | $0.00007 | $0.01136 |
| Sonnet 5 | $0.00003 | $0.00454 |
| Haiku 4.5 | $0.00001 | $0.00227 |
Grade A, and why
pi-research 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 10d 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Research (Dual-Track)
Research topics using Gemini (Google search grounding) and WebSearch in parallel, then Claude synthesizes. Two search tracks ensure resilience — if one fails, the other covers.
Execution
Bash invocation rules (v0.12.3+): Call
call-codex.sh/call-gemini.shin foreground synchronous mode withtimeout: 600000(Bash tool's 10-minute ceiling). Do not use&, do not setrun_in_background: true, do not usenohup— Claude Code 2026-04+ has an auto-background child-lifecycle regression that silently kills the process (output file stays 0 bytes). Userun_in_background: true+ BashOutput polling only as an exception when the call is genuinely expected to exceed 10 minutes.
1. Understand the research topic
$ARGUMENTS is the research topic. If the topic is vague, clarify with AskUserQuestion:
- Research purpose (tech selection? learning? problem solving?)
- Depth needed (quick overview vs deep analysis)
- Constraints (tech stack, budget, team size)
2. Gather project context (if relevant)
If the research topic relates to the current project, use Read/Glob/Grep to collect relevant context (dependencies, existing patterns, config). Keep context under 4000 chars — summarize if needed.
3. Dual-track research
Launch both tracks simultaneously in a single response:
┌─ Track A: Gemini (search grounding) ─┐
Research topic ──→│ │──merge──→ Step 5
└─ Track B: WebSearch (targeted queries)─┘
Track A — Gemini
Persist the full prompt (framing + project context) to a temp file, then call with the file on stdin (one invocation shape, no ARG_MAX exposure):
- Bash:
PROMPT_FILE=$(mktemp -t prism-research-XXXXXX.md) && echo "$PROMPT_FILE"— capture the path. - Use the Write tool to write the following prompt to that path (fill
$(date -u +%Y-%m-%d)with today's date; append project context from Step 2 at the end if any):
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.
- 10d ago First seen · 188 lines · 14 tokens per session scan A a5ca5fdb026e
pi-research is a command published in the GitHub repository tznthou/claude-prism (10 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 2,271 once invoked, about $0.0001 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 commands, from other repositories
greptile-review
Execute the full Greptile review cycle on a PR, looping until score meets threshold or circuit breaker triggers.
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.