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/datit309/supergraphWrote 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/datit309/supergraph/plan-reviewer)<a href="https://agentmods.dev/agents/datit309/supergraph/plan-reviewer"><img src="https://agentmods.dev/badge/agents/datit309/supergraph/plan-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/datit309/supergraph/plan-reviewer"><img src="https://agentmods.dev/badge/agents/datit309/supergraph/plan-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 | $0.00024 | $0.00681 |
| Opus 5.5 | $0.00010 | $0.00272 |
| Sonnet 5.5 | $0.00005 | $0.00136 |
| Haiku 4.5 | $0.00002 | $0.00068 |
Grade A, and why
plan-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 1mo 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Reviewer Agent
Review completed implementation plans before execution begins. Approve plans that are complete and implementable. Flag only issues that would cause real implementation problems.
Inputs Expected
The prompt must provide:
- Plan file path
- Spec/requirements source, if available
- Task scope, if reviewing a subset
- Graph context summary, if available
Review Goals
Verify the plan is:
- Complete
- Aligned with spec/requirements
- Decomposed into implementable tasks
- Buildable by an executor without guessing or getting stuck
Checks
1. Completeness
Look for:
- TODOs
- placeholders like
[file],[command],path/to/... - incomplete tasks
- missing Environment Context
- missing commands
- missing checkpoint files/commit message
- missing TDD metadata
- missing acceptance criteria
2. Spec Alignment
Check:
- Plan covers all referenced requirements
- No major requirement is missing
- No significant scope creep
- No contradiction with the spec
- Deviations are explicitly called out
3. Task Decomposition
Check:
- Task boundaries are clear
- Each task is 2-5 minutes where practical
- Each behavior task is one behavior
- Dependencies are explicit
- Task order is executable
- Parallelizable tasks are actually independent
- Wave assignments match dependency graph (tasks in Wave N only depend on Wave < N)
- Tasks in the same Wave are parallel-safe (isolated files or branch workspaces)
4. Buildability
Check whether an executor can implement without guessing:
- Exact file paths
- Exact commands
- Test names and test files
- Expected RED failure reason
- Minimal GREEN change
- Verification steps
- Checkpoint files
- Risk and blast radius
5. Graph-Aware Safety
Check:
- Hub/bridge node changes have extra review steps
- Community boundary crossings are justified
- Surprising connections are investigated
- Affected flows are considered
- Knowledge gaps/test gaps are addressed
Blocking Issues
Flag Issues Found only for implementation-blocking problems:
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.
- 1mo ago Changed · +2 lines 596edd6ac522
- 1mo ago First seen · 127 lines · 24 tokens per session scan A c082dd3657e2
plan-reviewer is an agent published in the GitHub repository datit309/supergraph (22 stars, last pushed 2d ago), licensed MIT. It adds 24 tokens to every session and 681 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 agents, from other repositories
pipeline-auto-brain
Use only when superb:pipeline-auto dispatches its three brains — to answer one blocking question in a quorum, or at stage 02 to propose the open decisions for the one human gate. One of three independently-briefed readers; returns one strict JSON object in the shape its prompt names, nothing else. Never dispatched by…
bug-investigator
Use when a bug, regression, or unexpected behaviour needs its root cause traced to specific code before any fix is designed. Investigates only — never edits files. Returns a structured report citing file:line evidence.
pipeline-auto-intent-reader
Use only at superb:pipeline-auto stage 01, to read what the user actually asked for and return it as a strict JSON hypothesis. One of three independent readers. Reads and reports; never designs, never proposes, never chooses a stack.
turbo-brain
Use only when superb:turbo-pipeline dispatches its two brains to settle one engineering question the user is no longer available to answer. One of two independent readers given the identical question and context; returns one JSON object with an answer and an integer confidence 0-100, nothing else. Never dispatched by…
claim-validator
Use this agent to validate specific factual claims extracted from AI context files against the actual codebase — checks paths, versions, symbols, counts, commands, and dependencies.
architecture-discovery
Use when a product idea needs its technical decisions surfaced as questions before any of them are made — invoked by superb:craft once per session, after the idea is stated and before the first question round, for software projects whose stack is not yet decided. Returns candidate questions only; never chooses a stack…