Reviews that find what humans miss
Graph-powered PR review with blast radius detection, structural analysis, and implementation planning at 2.75x the efficiency of exploration-based approaches.
2.75x
Fewer tokens
vs Plan-Mode exploration on the same change set
2.6x
Faster
3m 24s vs 8m 50s
39/40
Quality score
scored on the blueprint-quality rubric (v5 progressive template)
0
Agent spawns
Graph replaces exploration
Reviews that nitpick style miss architectural problems
Line-by-line misses the big picture
Traditional code review catches typos and style issues but misses structural problems — broken dependency chains, untested callers, permission boundary violations.
Planning burns your token budget
Plan Mode spawns 3+ agents for discovery, consuming 204K tokens before writing a single line. That's 99.4% of your budget spent on reading, not writing.
Vague plans produce vague code
Without forced structure, AI plans skip preservation boundaries, miss edge cases, and produce "Approach" paragraphs instead of per-file implementation specs.
Structural review powered by the code graph
Composure's review maps every change against the code graph. Every review checks: blast radius (callers reached by the change) · untested callers · decomposition thresholds · a diff-scoped security scan (Semgrep + secrets sweep + graph-weighted exposure ranking) · your own project-authored rules. Write a rule once — every review enforces it automatically. Blueprint planning uses the same graph for instant discovery, then progressive refinement with a structured template forces detailed per-file specs. The result: plans that catch design flaws during planning, not implementation.
See it in the field. In a recent client campaign, the review gate surfaced BLOCKING findings mid-run — two security findings caught by dedicated reviewer agents and fixed in-session, with the loopback taking four minutes of active time. The session record is public:
$/composure:review$→ Changes: src/lib/auth.ts, src/hooks/useAuth.ts$→ Impact: 3 files direct, 7 files indirect$→ Risk: Medium (auth module, 12 callers)$→ Untested: handleLogin() — 12 callers, 0 tests$→ Decomposition: useAuth.ts at 180 lines (threshold: 200)$Blueprint quality evolution:$ v1 (old template): 28/40$ v3 (new template): 34/40$ v5 (progressive): 39/40 — surpassed Plan ModeHow it works
Classify the work
Blueprint identifies whether this is a new feature, enhancement, refactor, bug fix, or migration — each type gets different questions and analysis depth.
Graph-powered discovery
Instead of spawning agents, query the code graph for related files, callers, and dependencies. 11 queries vs 76 agent calls — 6.9x more efficient.
Progressive refinement
Checkpoints at each step let you shape the plan through conversation. By the time the blueprint is written, most questions are already resolved.
Implementation spec, not paragraphs
The template forces per-file specs with exact conditions, signatures, and preservation boundaries. Writing this level of detail catches design flaws that vague plans miss.