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/datit309/supergraph/plan-reviewergit clone --depth 1 https://github.com/datit309/supergraphWhat 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 | $0.00024 | $0.00645 |
| Opus 5 | $0.00012 | $0.00322 |
| Sonnet 5 | $0.00005 | $0.00129 |
| Haiku 4.5 | $0.00002 | $0.00064 |
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 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 — 127 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
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:
- Missing spec requirement
- Contradictory plan steps
- Placeholder or incomplete content
- Task too vague to act on
- Missing Environment Context
- Missing TDD metadata for behavior changes
- Missing expected RED failure
- Missing acceptance criteria
- Missing checkpoint files
- Dependency/order problem
- Risk that executor will build wrong thing or stall
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 · 127 lines · 24 tokens per session scan A c082dd3657e2
plan-reviewer is an agent published in the GitHub repository datit309/supergraph (21 stars, last pushed 4d ago), licensed MIT. It adds 24 tokens to every session and 645 once invoked, about $0.0001 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
architect
../../agents/architect.md.
implementer
../../agents/implementer.md.
reviewer
../../agents/reviewer.md.
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.
context-auditor
Use this agent for deep analysis of a repository's AI context files — discovers all context files across tool ecosystems, assesses staleness, and identifies cross-document drift and contradictions.
knowledge-sources
This is a reference for the researcher agent. Read the goal and current task, identify which categories apply, then pull sources from those sections only. Ignore irrelevant categories — don't load noise.