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-ask-codex)<a href="https://agentmods.dev/commands/tznthou/claude-prism/pi-ask-codex"><img src="https://agentmods.dev/badge/commands/tznthou/claude-prism/pi-ask-codex.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 | $0.00015 | $0.00717 |
| Opus 5 | $0.00008 | $0.00358 |
| Sonnet 5 | $0.00003 | $0.00143 |
| Haiku 4.5 | $0.00002 | $0.00072 |
Grade A, and why
pi-ask-codex 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ask Codex
Forward the user's question to Codex CLI, get OpenAI's perspective.
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. Build the prompt
Use $ARGUMENTS as the prompt. If the question involves project code, read relevant files with the Read tool and append them.
2. Call Codex
Wrap the question in the one-shot framing below (the framing prefix is fixed; $ARGUMENTS is the user's question verbatim):
CLAUDE_PRISM_TIMEOUT=300 CLAUDE_PRISM_CALLER=pi-ask-codex ~/.claude/scripts/call-codex.sh "You get exactly one turn: do not ask clarifying questions. If context is missing, state your assumptions and answer anyway. Lead with your answer, then reasoning. Be concise by default — expand only where the question demands depth.
Question:
$ARGUMENTS"
If code context is needed, pipe it via stdin (avoids ARG_MAX limits):
echo "Relevant code:
$(code content)" | CLAUDE_PRISM_TIMEOUT=300 CLAUDE_PRISM_CALLER=pi-ask-codex ~/.claude/scripts/call-codex.sh "You get exactly one turn: do not ask clarifying questions. If context is missing, state your assumptions and answer anyway. Lead with your answer, then reasoning. Be concise by default — expand only where the question demands depth.
Question:
$ARGUMENTS"
3. Handle failures
If Codex fails (script exits non-zero or CLI not found):
- Claude answers the question directly.
- Include the specific failure reason from stderr (the script classifies errors as TIMEOUT, RATE_LIMIT, AUTH_ERROR, SANDBOX, NETWORK, CLI_ERROR, or CLI_NOT_FOUND).
- Note in output: "⚠️ Codex unavailable ([reason]) — answering with Claude only. For multi-provider perspectives, try
/pi-askall."
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 · 58 lines · 15 tokens per session scan A f402ef5c3203
pi-ask-codex is a command published in the GitHub repository tznthou/claude-prism (10 stars, last pushed today), licensed MIT. It adds 15 tokens to every session and 717 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.
logic-diff
Check two code versions for semantic equivalence — use after a refactor or rewrite.
challenge
Adversarial review — run pre-mortem, war-game, and logic-torturing analysis on current changes.
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.