When AI Coding Rituals Become the Bottleneck: Why a 300M Token/Day User Gutted Superpowers
Teams adopting AI-coding agents often inherit heavy, ritualized pipelines designed for weaker models. At scale, those rituals become the dominant cost — multiplying token spend, latency, and context pollution — while the model's actual capability to self-correct inside a single context goes unused. The fix is risk-calibrated process, not process elimination.
Superpowers bundles 14 skills into a default pipeline that forces brainstorming, detailed planning, git worktrees, sub-agent dispatch, spec review, and quality review on every task, including single-line config changes. A user who runs this workflow at industrial scale — roughly 300 million tokens per day — reports that the sequential dependencies and repeated context handoffs between agents multiply token consumption and wall-clock time far beyond what the actual code change requires. The process artifacts (design docs, plans, review reports) often outweigh the code change itself, and the model's attention shifts from solving the problem to proving process compliance.
The core failure is a mismatch between task risk and process intensity. Rules written as absolute mandates — "if there's a 1% chance a skill applies, call it" or "no production code without a failing test first" — leave the model no room to calibrate its approach. In the GPT-5.6 era, where a single strong model can understand, modify, test, and correct code within one context, this fixed heavy pipeline compresses the model's effective autonomy rather than enhancing it.
A local experiment stripped the skill set from 14 to 6 lightweight versions and cut the core rules from 3,207 lines to 110. The result was a three-tier system — Lite, Standard, Strict — that matches process intensity to actual risk, reserving sub-agents and independent reviews for security, payments, and major refactoring. The takeaway is not that process is bad, but that uncalibrated process becomes a tax that wastes tokens, attention, and time on low-risk work while creating a false sense of security on high-risk work.
Superpowers' pipeline is a textbook case of process calcification: rules written for unstable early agents survived into an era where a single strong model can self-correct inside one context, turning helpful scaffolding into deadweight.
The cost model reveals that token waste is not in generated code but in repeated context handoffs — the same requirements and diffs get read three or four times by different agents, each time rebuilding judgment context from scratch.
Review agents create a dangerous asymmetry: they can flag style preferences as defects but carry no accountability for false positives, forcing the main agent to spend tokens adjudicating review quality instead of code quality.
The '1% rule' is an anti-pattern for AI workflows — it converts low-confidence triggers into high-frequency process loads, exactly the opposite of how risk-based engineering should work.
Cutting 3,207 lines of rules to 110 is not just simplification; it proves the original complexity was rule-stacking, not problem-inherent. The engineering problem didn't demand 14 skills; the process design did.
The three-tier Lite/Standard/Strict model is effectively a risk-budgeting system for AI workflows — it reserves expensive multi-agent review for changes where the cost of failure justifies the cost of process, and lets everything else run lean.
The mandatory skill pipeline imposes a growing discipline cost that slows down capable models. A direct comparison shows CC4.8 takes nearly twice as long as Codex with superpowers on the same task, reinforcing the bottleneck. The view that the skills actively constrain a strong model's native ability rather than enhancing it surfaces as a core objection.
Already trapped by this; the discipline cost is getting higher and higher.
5.6's capability is already very strong. I feel these skills just constrain the model's ability.
This problem is even worse in CC4.8. Codex plus superpowers takes half an hour; CC4.8 takes almost an hour, tested on the same issue.