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/PraveenJayaprakash-JP/repomemoryWrote 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/praveenjayaprakash-jp/repomemory/review)<a href="https://agentmods.dev/commands/praveenjayaprakash-jp/repomemory/review"><img src="https://agentmods.dev/badge/commands/praveenjayaprakash-jp/repomemory/review/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/praveenjayaprakash-jp/repomemory/review"><img src="https://agentmods.dev/badge/commands/praveenjayaprakash-jp/repomemory/review.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 | $0.00000 | $0.00715 |
| Opus 5 | $0.00000 | $0.00358 |
| Sonnet 5 | $0.00000 | $0.00143 |
| Haiku 4.5 | $0.00000 | $0.00072 |
Grade A, and why
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 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/review
Description
Performs a structured code review on unstaged/staged changes (git diff) or a specified file/scope. Runs consistency checks against project conventions (CLAUDE.md) and outputs findings with severity levels.
Usage
/review # Reviews all unstaged/staged changes
/review <file-or-scope> # Reviews a specific file or directory
Options
| Flag | Description |
|---|---|
--full |
Deep review: checks code complexity, dependency patterns, test coverage gaps |
--quick |
Surface review: only checks naming, formatting, obvious antipatterns |
--security |
Security-focused: skips style/performance, deep-dives on OWASP Top 10 |
Flags can be combined.
/review --security --full runs both security checks and deep analysis.
Process
The review follows these steps:
- Identify scope – Runs
git diff(cached + unstaged) for unspecified scope; usesgit diff -- <file-or-scope>if a path is given. - Run check categories (adjusted by flags):
- Security: injection, XSS, auth mistakes, secret leaks, unsafe deserialization, path traversal.
- Performance: unnecessary allocations, missing memoization, sync IO in hot paths, large loops.
- Type safety: missing
strictenforcement,anyusage, unsafe type assertions, misuse of generics. - Error handling: swallowed errors, bare try/catch, missing error boundaries, improper error propagation.
- Verify conventions – Read
<workspace>/CLAUDE.mdif it exists; flag deviations in naming, module structure, export style, comment expectations. - Classify findings – Each finding gets a severity:
critical– Bug, security vulnerability, or definite crash.warning– Likely issue or convention violation.info– Suggestion or minor improvement.
- Suggest fixes – Provide exact file:line references and concrete code snippets for critical and warning findings.
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 · 77 lines · 0 tokens per session scan A 60772f0a71e0
review is a command published in the GitHub repository PraveenJayaprakash-JP/repomemory (1 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 715 tokens. 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
review
Structured code review with severity categorization (distinct from Claude Code's PR review).
review-codex
Adversarial security review via OpenAI model — second opinion from a different AI.
review
Pre-PR code review by a staff engineer sub-agent.
wire-check
Pre-commit quality gate — verify everything is wired up.
sdd-apply
Implement SDD tasks — writes code following specs and design.
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.