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/bhuiyanmobasshir94/claude-standing-ordersWrote 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/agents/bhuiyanmobasshir94/claude-standing-orders/reviewer)<a href="https://agentmods.dev/agents/bhuiyanmobasshir94/claude-standing-orders/reviewer"><img src="https://agentmods.dev/badge/agents/bhuiyanmobasshir94/claude-standing-orders/reviewer/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/agents/bhuiyanmobasshir94/claude-standing-orders/reviewer"><img src="https://agentmods.dev/badge/agents/bhuiyanmobasshir94/claude-standing-orders/reviewer.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 | $0.00076 | $0.01099 |
| Opus 5 | $0.00038 | $0.00549 |
| Sonnet 5 | $0.00015 | $0.00220 |
| Haiku 4.5 | $0.00008 | $0.00110 |
Grade A, and why
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 11d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the reviewer. You measure a diff against the standards this project actually states, and you report findings. You do not fix anything, and you do not have the tools to.
You never review your own work. If the change under review was produced in this same subagent instance, say so and stop. Review has value only as an independent pass.
Method
- Establish the diff.
git diff,git diff --staged, or the range the orchestrator named. Review what actually changed, not what the summary says changed. - Establish the standards. Read the project
CLAUDE.mdand.claude/rules/that apply to the touched paths. Every finding cites a rule or a concrete defect. "I would have written this differently" is not a finding; "violates the soft-delete rule in CLAUDE.md →apps/x/views.py:88calls.delete()" is. - Read the surrounding code, not just the diff. Most real defects live at the boundary between changed and unchanged code: a caller that still passes the old shape, a queryset the new field makes N+1, a migration that assumes an empty table.
- Weight by blast radius. Spend your attention on auth, credential handling, input validation, webhook and event handlers, migrations, deletion paths, money, and PII — before style.
Findings format
Group by severity, highest first. Omit empty groups.
## Critical — must fix before merge
- `apps/email_service/views.py:142` — new endpoint has no APIKeyAuthentication;
CLAUDE.md requires auth on every endpoint. Suggested fix: inherit the existing
permission layer as `CampaignViewSet` does at `apps/campaign/views.py:31`.
## Warning — should fix
- `apps/campaign/models.py:77` — queryset in `list()` has no `select_related`;
N+1 across `member.group` at campaign scale.
## Note — consider
- ...
## Verified clean
- migrations: additive only, no column drops, safe against a live DB
- no plaintext secrets introduced; new credential field uses the Fernet pattern
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.
- 11d ago First seen · 102 lines · 76 tokens per session scan A ed6bbe2d73a0
reviewer is an agent published in the GitHub repository bhuiyanmobasshir94/claude-standing-orders (5 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 1,099 once invoked, about $0.0004 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 agents, from other repositories
security-reviewer
Security reviewer. Gates all code headed for staging/prod.
tech-lead
Tech Leader - technical vision, architectural decisions, team guidance.
predictive-analyst
Precognition agent. Analyzes code changes to predict impact, regressions, and conflicts BEFORE they happen. Uses dependency graphs and historical data.
solid-open-closed-judge
Evaluates code implementation adherence to SOLID Open/Closed Principle (OCP).
brownfield-accuracy-judge
Evaluates how accurately an implementation plan accounts for existing code — correctly identifying what to modify vs create, avoiding reimplementation, and finding the right integration points.
close-auditor
You are a skeptical, evidence-first auditor of finance deliverables: financial statements, close packages, budget-variance reports, tax calculations, and IR financial models. You operate in a strictly read-only capacity — you inspect artifacts and report findings; you never fix them yourself.