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/marcusgoll/Spec-FlowWrote 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/marcusgoll/spec-flow/review)<a href="https://agentmods.dev/commands/marcusgoll/spec-flow/review"><img src="https://agentmods.dev/badge/commands/marcusgoll/spec-flow/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/marcusgoll/spec-flow/review"><img src="https://agentmods.dev/badge/commands/marcusgoll/spec-flow/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 | $0.00014 | $0.02290 |
| Opus 5.5 | $0.00006 | $0.00916 |
| Sonnet 5.5 | $0.00003 | $0.00458 |
| Haiku 4.5 | $0.00001 | $0.00229 |
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 2mo 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 — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/review — On-Demand Code Review
Current Branch: !git branch --show-current 2>/dev/null || echo "none"
Uncommitted Changes: !git diff --name-only HEAD 2>/dev/null | head -10
Staged Changes: !git diff --cached --name-only 2>/dev/null | head -10
Active Feature: @specs/*/state.yaml (find most recent by mtime)
Voting Config: @.spec-flow/config/voting.yaml
Review Modes:
| Mode | Flag | Speed | Use Case |
|---|---|---|---|
| Single-agent | --single (default) |
~2 min | Quick sanity check |
| Multi-agent voting | --voting |
~6 min | Critical decisions, pre-merge |
Scope Options:
| Scope | Flag | What's Reviewed |
|---|---|---|
| Changes | --scope changes (default) |
Uncommitted + staged changes |
| All | --scope all |
Entire feature directory |
Risk Level: LOW — Read-only analysis, no code modifications
Step 1: Parse Arguments
Extract flags from $ARGUMENTS:
| Flag | Variable | Default |
|---|---|---|
--voting |
USE_VOTING | false |
--single |
USE_VOTING | false |
--scope changes |
SCOPE | "changes" |
--scope all |
SCOPE | "changes" |
Step 2: Detect Review Scope
If SCOPE = "changes":
-
Get list of changed files:
git diff --name-only HEAD git diff --cached --name-only -
If no changes found:
- Inform user: "No uncommitted changes detected"
- Ask: Switch to
--scope allor exit?
-
Display changed files (max 15, then "and N more...")
If SCOPE = "all":
-
Detect active feature directory from:
- Current branch name matching
specs/*/pattern - Most recent
specs/*/state.yamlby modification time - Fall back to current working directory
- Current branch name matching
-
Display: "Reviewing entire feature: {feature_dir}"
Step 3: Gather Review Context
Do NOT create temp files. Gather context in memory:
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.
- 2mo ago First seen · 334 lines · 14 tokens per session scan A f56b466feb82
review is a command published in the GitHub repository marcusgoll/Spec-Flow (97 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 2,290 once invoked, about $0.0001 per session on Opus 5.5. 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 commands, from other repositories
quality-gate
Command "quality-gate" from VoDaiLocz/kilo-kit-mcp, covering ✅ quality gate command, workflow, gates, gate 1: pre-execution and gate 2: per-behavior.
pi-fact-check
Fact-check content via Gemini search + Claude verification — cross-provider claim validation.
pi-askall
Ask both Codex and Gemini the same question — get three perspectives with Claude synthesis.
review-spec
A command that reviews a software specification for accuracy, internal quality, and readiness for implementation. A specification describes what a feature should do and provides the reference for building it.
pi-plan
Multi-provider implementation planning — consult Codex and Gemini for architectural perspectives. Trigger: when the task involves architectural decisions, tech stack selection, evaluating multiple approaches, migration strategy, or complex implementation with multiple viable paths. Do NOT trigger for simple task…
r-audit
You are running the /r-audit full codebase audit. This command dispatches multiple reviewer and qa subagents in parallel to scan the entire codebase for latent issues, then synthesizes findings into a structured AUDIT.md.