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 skills/datit309/supergraph/reviewnpx skills add datit309/supergraph --skill reviewgit 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 | $0.01668 |
| Opus 5 | $0.00012 | $0.00834 |
| Sonnet 5 | $0.00005 | $0.00334 |
| Haiku 4.5 | $0.00002 | $0.00167 |
Grade A, and why
review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/supergraph:review
Final gate before merge. Graph-enhanced review with plan awareness.
Prerequisites
/supergraph:fixcompleted (tests pass, lint clean)
Usage
/supergraph:review | plan auth-login | plan auth-login task 2
Steps
0. Announce
"🔍 /supergraph:review — starting graph-enhanced code review..."
1. Select Plan Context
0 plans → skip | 1 → use | >1 → ask | plan <slug> → match.
Parse tasks, scope to task N if provided.
2. Capture Git Range
BASE_SHA=$(git rev-parse origin/master || git rev-parse origin/main || git rev-parse HEAD~1)
HEAD_SHA=$(git rev-parse HEAD)
git diff --stat "$BASE_SHA..$HEAD_SHA" && git diff --name-only "$BASE_SHA..$HEAD_SHA"
Use plan checkpoint commits as range if available. No changed files → check plan for incomplete tasks.
3. Graph Analysis (tiered)
Reindex first for CBM_PROJECT (see references/codebase-memory-contract.md#Lifecycle): index_status; if stale/degraded → index_repository (skip if BASE_SHA unchanged and .supergraph-env fresh). Then codebase-memory-mcp detect_changes, trace_path, get_graph_schema.
Tiered recipes (pick by blast radius):
- Micro (≤2 files, <20 lines, no hub/bridge):
cycles+test-gapsonly (0.04s) - Standard (≤5 files, no cross-boundary):
cycles/hubs/test-gaps+ optionalcross-boundary - Full (>5 files or hub/bridge/cross-boundary): all
cycles, hubs, bridges, test-gaps, complexity, cross-boundary(0.12s). Per file:query_graph(query_type="tests", target=file).
3b. Serena (optional, selective): See serena/SKILL.md:Setup. If scan not run, call initial_instructions first. Only for hub/bridge or complexity>10 files: find_referencing_symbols/find_implementations per symbol and get_diagnostics_for_file per file. Otherwise skip. Pass as "Serena findings". Skip if unavailable.
4. Dispatch Code Reviewer (tiered, parallel with tests)
Tiered (pick by blast radius):
- Micro (≤2 files, <20 lines, no hub/bridge): skip code-reviewer agent —
tests+lint+cycles+test-gapsđủ,Criticalchỉ từtests/lint/circular(LLM 30-60s saved) - Standard (≤5 files, no cross-boundary): Stage1 Spec Compliance only, parallel with tests
- Full (>5 files or hub/bridge/cross-boundary): 2-stage (Spec→Quality), parallel with tests. Join before Step 6.
Agent(subagent_type="supergraph:code-reviewer", prompt="Review BASE_SHA..HEAD_SHA. Spec first, then quality (Standard: Stage1 only). BASE_SHA/HEAD_SHA, git diff --stat + git diff (first 300 lines, or --name-only + snippets for large diffs), Graph: hubs/bridges/surprise/flows/gaps, Serena findings, Plan requirements. Output: strengths, Critical/Important/Minor, verdict YES|WITH_FIXES|NO")
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 · 142 lines · 24 tokens per session scan A 550e12cea07c
review is a skill published in the GitHub repository datit309/supergraph (21 stars, last pushed 5d ago), licensed MIT. It adds 24 tokens to every session and 1,668 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 skills, from other repositories
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…
migrate
Inventory an existing spec-driven project and apply bounded migrations to jig defaults: report, adopt-layout, rename-decisions, split-slices, slice-to-spec, seed-decisions, and copy-machinery. Use when the user says migrate this project to jig, adopt jig here, this repo already has specs — set up jig, scaffold-init…
adr-workflow
Scaffold, accept, index, and link Architectural Decision Records (ADRs). Use when the user says "write an ADR", "record this decision", "resolve [deferred item] with an ADR", "supersede ADR-NNNN", or otherwise wants to capture a hard-to-reverse decision in docs/decisions/. Also use when a refinement-todo entry needs…
bug-fix
Drive the teeth-gated lifecycle for reported defects: diagnose root cause, prove it, and prevent regression through REPORTED → DIAGNOSING → ROOTCAUSED → FIXING → REVIEWED → DONE, with VERIFIED, ESCALATED, and RESOLVEDONMAIN paths where needed. Auto-fires on fix this bug, debug this, root-cause this, this regressed…
analyze
Cross-artifact consistency report for jig specs — a non-destructive six-category audit at CRITICAL/HIGH/MEDIUM/LOW severity, covering duplication, ambiguity, underspecification, principle violations, coverage gaps, and terminology drift. Auto-triggers when you say analyze this spec, check for inconsistencies, audit…
arch-review
Team baseline for architecture, design-doc, and RFC review — produces summary, strengths, concerns, and open questions. Auto-triggers when you say review this design, review this architecture, review this proposal, review my RFC, poke holes in this proposal, is this design sound, or critique this tech spec. Defers to…