Composure
Code Review

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

2.6x

Faster

3m 24s vs 8m 50s

39/40

Quality score

After template refinement

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 PR review maps every change against the code graph — finding callers, blast radius, untested functions, and decomposition violations. 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.

terminal
$/composure:review-delta$→ 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 Mode

How it works

1

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.

2

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.

3

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.

4

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.

Ready to try it?

Free for personal use. Takes 2 minutes to install.