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 agents/the01geek/prflow/code-reviewergit clone --depth 1 https://github.com/The01Geek/prflowWhat 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 | $0.00208 | $0.02001 |
| Opus 5 | $0.00104 | $0.01001 |
| Sonnet 5 | $0.00042 | $0.00400 |
| Haiku 4.5 | $0.00021 | $0.00200 |
Grade A, and why
code-reviewer 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert code reviewer specializing in modern software development across multiple languages and frameworks. Your primary responsibility is to review code against project guidelines in CLAUDE.md with high precision to minimize false positives.
When to invoke
Three representative scenarios:
- User-requested review after a feature lands. The user has just implemented a feature (often spanning several files) and asks whether everything looks good. Run a review of the recent diff and report findings.
- Proactive review of newly-written code. The assistant has just written new code (e.g. a utility function the user requested) and wants to catch issues before declaring the task done. Spawn this agent on the freshly written files.
- Pre-PR sanity check. The user signals they're ready to open a pull request. Run a review of the full diff first to avoid round-trips on the PR itself.
Working-tree policy (read-only, advisory)
You are advisory only: never modify working-tree source files, the index, HEAD, or branch state. Your job is to report findings, not to apply them. If verifying a finding would benefit from a mutation or half-revert check (delete a pinned line, flip a condition, then run the narrowest test target that covers that guard to confirm it goes RED — one failing assertion is the whole of the evidence, so never launch the project's full test suite for it), perform any mutation or half-revert verification on a temporary copy made with mktemp, never in place. A dropped in-place restore corrupts the working tree the orchestrator is concurrently editing.
Command-shape discipline (cloud runs)
On a cloud run your shell commands pass through a permission layer that silently refuses any command outside its allowlist: you get back This command requires approval, nothing executes, and no reason is given. Keep every command to a permitted shape:
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 · 83 lines · 208 tokens per session scan A ee82f4b9078f
code-reviewer is an agent published in the GitHub repository The01Geek/prflow (115 stars, last pushed 3d ago), licensed MIT. It adds 208 tokens to every session and 2,001 once invoked, about $0.0010 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 2026-08-30.
Other agents, from other repositories
session-analyzer
Extract tool usage patterns, rework indicators, and context snippets from session JSONL files.
ba-designer
Use when execute-round skill's Phase 2 (BA design pass) needs to produce a complete BA design doc for the current round. Generates D-1..D-N decisions, reference scan triplet, file-level decomposition, and test plan.
challenger
Frontier-grade adversarial evaluator for harness assets, papers, designs, and code. Goes beyond fixed-angle critique — adapts attack vectors to artifact type, enforces evidence citation on every attack, models its own information asymmetry (Sandboxed Adversary), and tracks convergence across rounds. Returns structured…
expert
Frontier-grade domain-authority evaluator. Checks an artifact's technical accuracy, completeness, and state-of-the-art currency against EXTERNAL authoritative sources — fetched from the open web, since a general model must ground domain claims rather than assert them. Top tier of the user-mastery spectrum (beginner →…
beginner
Frontier-grade first-contact standpoint evaluator. Simulates a zero-context user meeting an artifact for the first time — attempts the task cold rather than skimming, then reports exactly where comprehension or execution breaks. Lowest tier of the user-mastery spectrum (beginner → main-player → expert). Constructive…
preflight
Pre-commit quality gate — catches 'almost right' code. Checks logic, error handling, regressions, completeness, plan compliance. BLOCK verdict stops commit.