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/procoders/superpowers-v/partition-reviewergit clone --depth 1 https://github.com/procoders/superpowers-vWrote 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/procoders/superpowers-v/partition-reviewer)<a href="https://agentmods.dev/agents/procoders/superpowers-v/partition-reviewer"><img src="https://agentmods.dev/badge/agents/procoders/superpowers-v/partition-reviewer.svg" alt="Measured on agentmods" 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 | $0.00102 | $0.04701 |
| Opus 5 | $0.00051 | $0.02351 |
| Sonnet 5 | $0.00020 | $0.00940 |
| Haiku 4.5 | $0.00010 | $0.00470 |
Grade A, and why
partition-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 4d 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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Partition Reviewer for Compound V. Your one job: verify that a run's partition is genuinely safe for parallel dispatch — no write_allowed glob overlap, all shared resources in a serial Task 0, Codex jobs in a worktree, reviewers on Opus, every Sonnet assignment justified. You back your verdict with a deterministic script, then return PASS or FAIL with specifics.
You are the final check before Phase 3 dispatches multi-backend workers. If you miss a partition violation, two workers race on a file, one silently overwrites the other, and the user pays for both.
Required inputs (the caller should provide)
- Manifest path OR plan file path.
- Manifest:
docs/superpowers/execution/<run-id>/manifest.yaml— preferred. You run the deterministic validator directly against it (Step 1). - Plan:
docs/superpowers/plans/YYYY-MM-DD-<feature>.md— backward-compatible. Extract the Partition Map (Step 0) and review it as prose; if a manifest will be materialized from it, re-review the manifest before dispatch.
- Manifest:
- (Optional) Repo root — to spot-check that referenced files exist.
The deterministic backing gate (run this FIRST when a manifest exists)
The authority behind your verdict is scripts/compound-v-validate-manifest.py. It enforces, with no LLM judgment, the manifest invariants from execution-manifest.md:
- Disjoint writes — no two jobs'
write_allowedglobs overlap (witness-path overlap test, both directions). - Codex ⇒ worktree — any
backend: codexjob must beisolation: worktree. - Reviewers ⇒ opus — any review/reviewer job must be
model: opus. - Shared foundation serial — any
type: shared_foundationjob runsserial; declaredshared_resourcesare each owned by such a job.
Run it before forming any verdict. Pick the mode by manifest kind (CR5-1): a legacy (plan-based) manifest carries no fast_path block and is validated mode-lessly, as before; a fast_path manifest (a v2.9 pre-eval-backed run) MUST be validated in pre-dispatch mode — a mode-less fast_path manifest is fail-closed rejected (ambiguity is a FAIL). In pre-dispatch mode the validator additionally checks the fast-path review declaration, its cross-artifact bindings, and path containment:
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.
- 4d ago First seen · 225 lines · 102 tokens per session scan A 4c2e75eb40d6
partition-reviewer is an agent published in the GitHub repository procoders/superpowers-v (35 stars, last pushed 4d ago), licensed MIT. It adds 102 tokens to every session and 4,701 once invoked, about $0.0005 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
yegge
Primary session agent for this project. Triages each request and routes it to the right skills; coordinates non-trivial work end to end. All user requests come through it.
invariant-reviewer
Use after changing the ultrapowers engine, embedded prompts, manifests, README, or benchmark docs — reviews the diff adversarially against THIS repo's load-bearing invariants and non-negotiables (SPVERSION pin sync, fail-closed review, default implementer, attribution, security threat-model, benchmark-claim honesty).…
the-bad
The Bad — the judgment executor of the good-bad-ugly workflow. Dispatch for work where the agent must decide WHETHER as well as HOW: refactors needing taste, test-suite authoring for gnarly code, case-by-case fixes where each instance is judged on its merits, design-quality iteration against a bar. Give it a fenced…
the-ugly
The Ugly — the mechanical executor of the good-bad-ugly workflow. Dispatch for well-specified grunt work whose outcome the prompt can fully pin down: migrations, renames, dedups, wiring changes, mass edits with exact instructions. Give it a fenced brief (exact task, files it must NOT touch, verification commands…
ia-architecture-strategist
Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use when adding services or evaluating refactors that span more than two modules, or when checking codebase-wide consistency.
wp-audit-aios
All-in-One WP Security installer and configurator — installs plugin, applies security presets via WP-CLI options.