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-code-review)<a href="https://agentmods.dev/commands/tznthou/claude-prism/pi-code-review"><img src="https://agentmods.dev/badge/commands/tznthou/claude-prism/pi-code-review.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 | $0.00017 | $0.03629 |
| Opus 5 | $0.00009 | $0.01814 |
| Sonnet 5 | $0.00003 | $0.00726 |
| Haiku 4.5 | $0.00002 | $0.00363 |
Grade A, and why
pi-code-review 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 7d 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 — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adversarial Code Review via Codex
Use Codex CLI to adversarially review code. Core value: the AI that wrote the code (Claude) is NOT the one reviewing it (Codex) — eliminates same-source blind spots. The reviewer's job is to break confidence in the change, not validate it.
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. Determine review scope
Based on $ARGUMENTS:
- No args: review
git diff --cached(staged changes) - File path: review the specified file
--diff: reviewgit diff(unstaged changes)--pr: review full PR diff (git diff main...HEAD)--verbose: also show issues that were filtered out (< 80 confidence) with their scores
1.5 Gather project guidelines
Search for project guideline files to use as compliance context:
# Check common locations for guideline files
for f in CLAUDE.md .claude/CLAUDE.md Agents.md .claude/Agents.md; do
[ -f "$f" ] && echo "=== $f ===" && cat "$f"
done
- If any guideline files are found, their content becomes part of the review context (passed to the provider and used in confidence scoring).
- If none are found, skip this dimension — do not fabricate guidelines.
- Keep the raw guideline text available for Step 5 (confidence scoring).
1.7 Gather historical PR comments (--pr mode only)
When using --pr mode, search for recurring review patterns on the same files:
- Get files in this PR:
git diff main...HEAD --name-only - Find recent merged PRs:
gh pr list --state merged --limit 10 --json number,title - For each (up to 5), fetch review comments on the same files:
gh api "repos/{owner}/{repo}/pulls/NUMBER/comments" \ --jq '.[] | select(.path == "TOUCHED_FILE") | {path, body}' - Include found comments as additional context in the Codex prompt (Step 3), prefixed with: "Historical Review Context (previous review comments on the same files — recurring issues are high-confidence signals):"
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.
- 7d ago First seen · 308 lines · 17 tokens per session scan A 3816fe135dc5
pi-code-review is a command published in the GitHub repository tznthou/claude-prism (10 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 3,629 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.